Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.9879. Min Act: -0.1700
Data Index: 4631949 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.8942. Min Act: -0.1700
Data Index: 1020036 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.8317. Min Act: -0.1700
Data Index: 7768543 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.7379. Min Act: -0.1700
Data Index: 3797588 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.7379. Min Act: -0.1700
Data Index: 312424 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.6442. Min Act: -0.1700
Data Index: 5409200 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.6129. Min Act: -0.1700
Data Index: 680752 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.5817. Min Act: -0.1700
Data Index: 7007449 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.5504. Min Act: -0.1700
Data Index: 8478078 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.5504. Min Act: -0.1700
Data Index: 1136976 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.5504. Min Act: -0.1700
Data Index: 375176 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.5192. Min Act: -0.1700
Data Index: 7139618 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4879. Min Act: -0.1700
Data Index: 24154 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4879. Min Act: -0.1700
Data Index: 3537819 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4879. Min Act: -0.1700
Data Index: 3116429 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4567. Min Act: -0.1700
Data Index: 2029048 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4567. Min Act: -0.1700
Data Index: 5834956 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4567. Min Act: -0.1700
Data Index: 338597 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4254. Min Act: -0.1700
Data Index: 6165707 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9879. Min Range: -6.9879
Max Act: 6.4254. Min Act: -0.1700
Data Index: 4564884 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19