Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6359 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.6597. Min Act: -0.1700
Data Index: 3129657 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.6597. Min Act: -0.1700
Data Index: 1583839 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.6597. Min Act: -0.1700
Data Index: 818881 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.5347. Min Act: -0.1700
Data Index: 8687544 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.4722. Min Act: -0.1700
Data Index: 6859393 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.4097. Min Act: -0.1700
Data Index: 4349431 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.3472. Min Act: -0.1700
Data Index: 4253459 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.2222. Min Act: -0.1700
Data Index: 4367826 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.1597. Min Act: -0.1700
Data Index: 4012682 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.1597. Min Act: -0.1700
Data Index: 7660825 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.1597. Min Act: -0.1700
Data Index: 3532606 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.1597. Min Act: -0.1700
Data Index: 839010 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.1597. Min Act: -0.1700
Data Index: 3757134 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.6597. Min Range: -15.6597
Max Act: 15.0347. Min Act: -0.1700
Data Index: 442772 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.6597. Min Range: -15.6597
Max Act: 14.9097. Min Act: -0.1700
Data Index: 3699691 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.6597. Min Range: -15.6597
Max Act: 14.9097. Min Act: -0.1700
Data Index: 2896720 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.6597. Min Range: -15.6597
Max Act: 14.9097. Min Act: -0.1700
Data Index: 3977156 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.6597. Min Range: -15.6597
Max Act: 14.9097. Min Act: -0.1700
Data Index: 5113686 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.6597. Min Range: -15.6597
Max Act: 14.7847. Min Act: -0.1700
Data Index: 8665905 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.6597. Min Range: -15.6597
Max Act: 14.8472. Min Act: -0.1700
Data Index: 6536181 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19