Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 71 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5962. Min Act: -0.1700
Data Index: 2497122 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5650. Min Act: -0.1700
Data Index: 1273465 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5962. Min Act: -0.1700
Data Index: 5019806 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5962. Min Act: -0.1700
Data Index: 2097061 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5650. Min Act: -0.1700
Data Index: 4793914 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5650. Min Act: -0.1700
Data Index: 772220 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5025. Min Act: -0.1700
Data Index: 5224572 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5337. Min Act: -0.1700
Data Index: 8092560 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5650. Min Act: -0.1700
Data Index: 7600052 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.4712. Min Act: -0.1700
Data Index: 8794234 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5025. Min Act: -0.1700
Data Index: 3590163 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5025. Min Act: -0.1700
Data Index: 2166006 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.4712. Min Act: -0.1700
Data Index: 4353586 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5337. Min Act: -0.1700
Data Index: 6103555 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.4712. Min Act: -0.1700
Data Index: 3262597 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.5025. Min Act: -0.1700
Data Index: 6670327 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.4400. Min Act: -0.1700
Data Index: 3216238 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.4712. Min Act: -0.1700
Data Index: 7711559 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.4712. Min Act: -0.1700
Data Index: 4278063 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5962. Min Range: -4.5962
Max Act: 4.4712. Min Act: -0.1700
Data Index: 4494101 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19