Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0680. Min Act: -0.1700
Data Index: 4042261 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0993. Min Act: -0.1700
Data Index: 3080634 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0055. Min Act: -0.1700
Data Index: 922942 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0368. Min Act: -0.1700
Data Index: 2991456 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0368. Min Act: -0.1700
Data Index: 3825154 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9743. Min Act: -0.1700
Data Index: 2327638 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0055. Min Act: -0.1700
Data Index: 1075949 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9430. Min Act: -0.1700
Data Index: 6193988 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9430. Min Act: -0.1700
Data Index: 4097141 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9430. Min Act: -0.1700
Data Index: 854439 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0055. Min Act: -0.1700
Data Index: 7314207 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9118. Min Act: -0.1700
Data Index: 5573695 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9118. Min Act: -0.1700
Data Index: 2464143 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9118. Min Act: -0.1700
Data Index: 1935250 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8493. Min Act: -0.1700
Data Index: 7319516 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8805. Min Act: -0.1700
Data Index: 5962507 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9118. Min Act: -0.1700
Data Index: 2004180 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9118. Min Act: -0.1700
Data Index: 5547089 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8493. Min Act: -0.1700
Data Index: 6021160 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8180. Min Act: -0.1700
Data Index: 3115499 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19