Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 990 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4997. Min Act: -0.1700
Data Index: 6181023 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4685. Min Act: -0.1700
Data Index: 2098221 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3122. Min Act: -0.1700
Data Index: 2659142 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4997. Min Act: -0.1700
Data Index: 5397718 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4685. Min Act: -0.1700
Data Index: 5222460 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4060. Min Act: -0.1700
Data Index: 7571289 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4372. Min Act: -0.1700
Data Index: 8565203 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3747. Min Act: -0.1700
Data Index: 7583255 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4372. Min Act: -0.1700
Data Index: 7764646 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3747. Min Act: -0.1700
Data Index: 370719 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3747. Min Act: -0.1700
Data Index: 3325518 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3435. Min Act: -0.1700
Data Index: 7324718 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3435. Min Act: -0.1700
Data Index: 6013065 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.4060. Min Act: -0.1700
Data Index: 1974698 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3435. Min Act: -0.1700
Data Index: 7178453 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3435. Min Act: -0.1700
Data Index: 1172525 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3122. Min Act: -0.1700
Data Index: 578286 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3122. Min Act: -0.1700
Data Index: 1793165 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.3122. Min Act: -0.1700
Data Index: 7854335 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4997. Min Range: -4.4997
Max Act: 4.2810. Min Act: -0.1700
Data Index: 1154210 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19