Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.7371. Min Act: -0.1700
Data Index: 6650497 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.6120. Min Act: -0.1700
Data Index: 3607960 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.5180. Min Act: -0.1700
Data Index: 1207590 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.5337. Min Act: -0.1700
Data Index: 832586 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.5337. Min Act: -0.1700
Data Index: 5694171 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.5180. Min Act: -0.1700
Data Index: 5959290 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4867. Min Act: -0.1700
Data Index: 2917506 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.5024. Min Act: -0.1700
Data Index: 6109403 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.5024. Min Act: -0.1700
Data Index: 3597602 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4867. Min Act: -0.1700
Data Index: 7201810 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.5024. Min Act: -0.1700
Data Index: 7239382 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4710. Min Act: -0.1700
Data Index: 3607959 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4867. Min Act: -0.1700
Data Index: 6153464 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4397. Min Act: -0.1700
Data Index: 3355 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4397. Min Act: -0.1700
Data Index: 3598214 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4240. Min Act: -0.1700
Data Index: 8571988 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4084. Min Act: -0.1700
Data Index: 4892451 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4084. Min Act: -0.1700
Data Index: 1549358 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.4084. Min Act: -0.1700
Data Index: 3898937 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7371. Min Range: -3.7371
Max Act: 3.3770. Min Act: -0.1700
Data Index: 1376614 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19