Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.0489. Min Range: -14.0489
Max Act: 14.0489. Min Act: -0.1700
Data Index: 4954759 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0489. Min Range: -14.0489
Max Act: 13.4864. Min Act: -0.1700
Data Index: 6103482 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0489. Min Range: -14.0489
Max Act: 13.4239. Min Act: -0.1700
Data Index: 5559790 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0489. Min Range: -14.0489
Max Act: 13.1114. Min Act: -0.1700
Data Index: 8415952 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0489. Min Range: -14.0489
Max Act: 13.0489. Min Act: -0.1700
Data Index: 4734911 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0489. Min Range: -14.0489
Max Act: 13.0489. Min Act: -0.1700
Data Index: 1703297 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.9239. Min Act: -0.1700
Data Index: 8129813 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.8614. Min Act: -0.1700
Data Index: 8691716 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.7989. Min Act: -0.1700
Data Index: 6232949 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.8614. Min Act: -0.1700
Data Index: 3160077 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.7989. Min Act: -0.1700
Data Index: 2202294 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.7364. Min Act: -0.1700
Data Index: 4877010 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.8614. Min Act: -0.1700
Data Index: 3766790 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.6739. Min Act: -0.1700
Data Index: 1124722 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.7989. Min Act: -0.1700
Data Index: 3579078 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.6739. Min Act: -0.1700
Data Index: 8213185 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.7364. Min Act: -0.1700
Data Index: 1634914 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.6114. Min Act: -0.1700
Data Index: 6749680 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.5489. Min Act: -0.1700
Data Index: 4340220 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0489. Min Range: -14.0489
Max Act: 12.6114. Min Act: -0.1700
Data Index: 4116167 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19