Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4994 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.2864. Min Act: -0.1700
Data Index: 2164845 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.2551. Min Act: -0.1700
Data Index: 8089437 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.1926. Min Act: -0.1700
Data Index: 769206 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.0989. Min Act: -0.1700
Data Index: 4376494 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.0989. Min Act: -0.1700
Data Index: 4357202 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.0676. Min Act: -0.1700
Data Index: 4827500 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.0364. Min Act: -0.1700
Data Index: 7029482 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.0051. Min Act: -0.1700
Data Index: 7962523 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2864. Min Range: -7.2864
Max Act: 7.0051. Min Act: -0.1700
Data Index: 8088239 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.9739. Min Act: -0.1700
Data Index: 6099054 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.9739. Min Act: -0.1700
Data Index: 2289956 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.9739. Min Act: -0.1700
Data Index: 2239650 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.9426. Min Act: -0.1700
Data Index: 7331738 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.8801. Min Act: -0.1700
Data Index: 8689350 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.8489. Min Act: -0.1700
Data Index: 419242 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.8176. Min Act: -0.1700
Data Index: 6200978 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.8176. Min Act: -0.1700
Data Index: 2679049 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.8489. Min Act: -0.1700
Data Index: 4652948 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.8176. Min Act: -0.1700
Data Index: 985304 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2864. Min Range: -7.2864
Max Act: 6.8176. Min Act: -0.1700
Data Index: 300237 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19