Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.3593. Min Act: -0.1700
Data Index: 8405289 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1718. Min Act: -0.1700
Data Index: 4167344 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1718. Min Act: -0.1700
Data Index: 4179982 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1718. Min Act: -0.1700
Data Index: 4172850 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1093. Min Act: -0.1700
Data Index: 3259459 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 6688963 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 1610605 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 7501198 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 2612526 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.9218. Min Act: -0.1700
Data Index: 2283444 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.8280. Min Act: -0.1700
Data Index: 8505365 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7968. Min Act: -0.1700
Data Index: 351092 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7968. Min Act: -0.1700
Data Index: 6569131 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7655. Min Act: -0.1700
Data Index: 3589443 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.8280. Min Act: -0.1700
Data Index: 3730561 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7968. Min Act: -0.1700
Data Index: 308651 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7343. Min Act: -0.1700
Data Index: 5838195 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7343. Min Act: -0.1700
Data Index: 1892512 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7030. Min Act: -0.1700
Data Index: 1747749 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.7030. Min Act: -0.1700
Data Index: 6129996 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19