Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3179 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.9281. Min Act: -0.1700
Data Index: 8193909 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.8344. Min Act: -0.1700
Data Index: 1312067 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.8031. Min Act: -0.1700
Data Index: 1865012 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.6469. Min Act: -0.1700
Data Index: 1706775 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.5844. Min Act: -0.1700
Data Index: 4265517 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.5219. Min Act: -0.1700
Data Index: 7214581 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.5219. Min Act: -0.1700
Data Index: 5319161 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.4594. Min Act: -0.1700
Data Index: 7493438 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.4594. Min Act: -0.1700
Data Index: 7868573 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.4594. Min Act: -0.1700
Data Index: 85611 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.4594. Min Act: -0.1700
Data Index: 3358809 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.4281. Min Act: -0.1700
Data Index: 7180558 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3969. Min Act: -0.1700
Data Index: 7949113 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3969. Min Act: -0.1700
Data Index: 5697696 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3344. Min Act: -0.1700
Data Index: 5660411 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3656. Min Act: -0.1700
Data Index: 4116651 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3344. Min Act: -0.1700
Data Index: 755905 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3031. Min Act: -0.1700
Data Index: 4979626 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3344. Min Act: -0.1700
Data Index: 292487 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9281. Min Range: -5.9281
Max Act: 5.3344. Min Act: -0.1700
Data Index: 4647797 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19