Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5683 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8767. Min Range: -7.8767
Max Act: 7.8767. Min Act: -0.1700
Data Index: 2900342 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8767. Min Range: -7.8767
Max Act: 7.3142. Min Act: -0.1700
Data Index: 226454 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8767. Min Range: -7.8767
Max Act: 7.0642. Min Act: -0.1700
Data Index: 4757156 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8767. Min Range: -7.8767
Max Act: 7.0330. Min Act: -0.1700
Data Index: 7274258 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.9392. Min Act: -0.1700
Data Index: 7683935 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.9392. Min Act: -0.1700
Data Index: 2144599 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.9392. Min Act: -0.1700
Data Index: 6463433 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.8455. Min Act: -0.1700
Data Index: 723968 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.7830. Min Act: -0.1700
Data Index: 3537620 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.8142. Min Act: -0.1700
Data Index: 534998 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 3198732 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 5006788 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 1606310 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 3010603 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.6892. Min Act: -0.1700
Data Index: 5620790 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 3531566 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 6274087 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 1195105 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.6892. Min Act: -0.1700
Data Index: 1512939 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8767. Min Range: -7.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 7665206 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19