Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6196 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9447. Min Act: -0.1700
Data Index: 3868368 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9130. Min Act: -0.1700
Data Index: 447701 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9289. Min Act: -0.1700
Data Index: 8203647 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9130. Min Act: -0.1700
Data Index: 1414082 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8972. Min Act: -0.1700
Data Index: 2180375 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9130. Min Act: -0.1700
Data Index: 5231757 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8972. Min Act: -0.1700
Data Index: 8393464 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 1554587 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 1051461 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 3366768 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 8194201 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8337. Min Act: -0.1700
Data Index: 4703318 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8337. Min Act: -0.1700
Data Index: 64934 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8337. Min Act: -0.1700
Data Index: 5517523 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8178. Min Act: -0.1700
Data Index: 8602505 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8178. Min Act: -0.1700
Data Index: 3524795 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8178. Min Act: -0.1700
Data Index: 3095617 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8178. Min Act: -0.1700
Data Index: 5278724 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8019. Min Act: -0.1700
Data Index: 2708609 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8178. Min Act: -0.1700
Data Index: 7420822 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19