Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1047. Min Range: -2.1047
Max Act: 2.1047. Min Act: -0.1700
Data Index: 1474605 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1047. Min Range: -2.1047
Max Act: 2.0880. Min Act: -0.1700
Data Index: 1407371 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1047. Min Range: -2.1047
Max Act: 2.0376. Min Act: -0.1700
Data Index: 5825559 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1047. Min Range: -2.1047
Max Act: 2.0207. Min Act: -0.1700
Data Index: 8239246 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1047. Min Range: -2.1047
Max Act: 2.0039. Min Act: -0.1700
Data Index: 825543 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9869. Min Act: -0.1700
Data Index: 4874714 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9700. Min Act: -0.1700
Data Index: 387568 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9700. Min Act: -0.1700
Data Index: 3176367 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9531. Min Act: -0.1700
Data Index: 5413994 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9531. Min Act: -0.1700
Data Index: 101277 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9191. Min Act: -0.1700
Data Index: 6590939 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9191. Min Act: -0.1700
Data Index: 3298648 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.8850. Min Act: -0.1700
Data Index: 1103510 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9191. Min Act: -0.1700
Data Index: 2541730 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9020. Min Act: -0.1700
Data Index: 3304709 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.8850. Min Act: -0.1700
Data Index: 7944127 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.9020. Min Act: -0.1700
Data Index: 7303234 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.8850. Min Act: -0.1700
Data Index: 6162002 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.8679. Min Act: -0.1700
Data Index: 1445278 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1047. Min Range: -2.1047
Max Act: 1.8850. Min Act: -0.1700
Data Index: 46632 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19