Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.5933. Min Act: -0.1700
Data Index: 68057 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.4058. Min Act: -0.1700
Data Index: 6648044 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.3121. Min Act: -0.1700
Data Index: 5275886 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.2808. Min Act: -0.1700
Data Index: 2834311 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.2183. Min Act: -0.1700
Data Index: 290437 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1871. Min Act: -0.1700
Data Index: 5095540 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1871. Min Act: -0.1700
Data Index: 7819545 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1558. Min Act: -0.1700
Data Index: 2507059 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1558. Min Act: -0.1700
Data Index: 27682 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1558. Min Act: -0.1700
Data Index: 1133491 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1246. Min Act: -0.1700
Data Index: 2360162 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1246. Min Act: -0.1700
Data Index: 1602755 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.1246. Min Act: -0.1700
Data Index: 1248545 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.0933. Min Act: -0.1700
Data Index: 7061921 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.0621. Min Act: -0.1700
Data Index: 4044504 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.0621. Min Act: -0.1700
Data Index: 8128751 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.0621. Min Act: -0.1700
Data Index: 3358169 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.0621. Min Act: -0.1700
Data Index: 4427323 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.0621. Min Act: -0.1700
Data Index: 1917778 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5933. Min Range: -5.5933
Max Act: 5.0308. Min Act: -0.1700
Data Index: 6949684 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19