Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4010 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.1693. Min Range: -15.1693
Max Act: 15.1693. Min Act: -0.1700
Data Index: 5599487 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.7943. Min Act: -0.1700
Data Index: 7945986 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.6068. Min Act: -0.1700
Data Index: 7248967 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.4193. Min Act: -0.1700
Data Index: 2502949 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.3568. Min Act: -0.1700
Data Index: 5411887 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.3568. Min Act: -0.1700
Data Index: 6200582 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.2943. Min Act: -0.1700
Data Index: 4784999 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.2318. Min Act: -0.1700
Data Index: 2596339 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.2318. Min Act: -0.1700
Data Index: 5737321 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.2318. Min Act: -0.1700
Data Index: 6730764 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.2318. Min Act: -0.1700
Data Index: 8186733 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1693. Min Act: -0.1700
Data Index: 523186 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1693. Min Act: -0.1700
Data Index: 8191837 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1693. Min Act: -0.1700
Data Index: 6927470 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1693. Min Act: -0.1700
Data Index: 5367766 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1693. Min Act: -0.1700
Data Index: 8202949 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1693. Min Act: -0.1700
Data Index: 4658155 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1693. Min Act: -0.1700
Data Index: 777906 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.0443. Min Act: -0.1700
Data Index: 6986890 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1693. Min Range: -15.1693
Max Act: 14.1068. Min Act: -0.1700
Data Index: 3018022 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19