Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1087 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.9563. Min Range: -16.9563
Max Act: 16.9563. Min Act: -0.1700
Data Index: 6664145 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.9563. Min Range: -16.9563
Max Act: 16.8313. Min Act: -0.1700
Data Index: 2401829 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.9563. Min Range: -16.9563
Max Act: 16.0813. Min Act: -0.1699
Data Index: 2542326 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.8313. Min Act: -0.1700
Data Index: 3249396 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.8313. Min Act: -0.1700
Data Index: 5464180 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.8313. Min Act: -0.1700
Data Index: 6702754 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.5813. Min Act: -0.1700
Data Index: 5093153 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.5813. Min Act: -0.1700
Data Index: 7752238 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.5813. Min Act: -0.1700
Data Index: 376565 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.4563. Min Act: -0.1700
Data Index: 3720825 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.3938. Min Act: -0.1700
Data Index: 4296803 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.3938. Min Act: -0.1700
Data Index: 5141940 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.3938. Min Act: -0.1700
Data Index: 4863565 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.3938. Min Act: -0.1700
Data Index: 6237524 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.3313. Min Act: -0.1700
Data Index: 453336 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.4563. Min Act: -0.1700
Data Index: 5184464 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.3313. Min Act: -0.1700
Data Index: 5061491 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.2688. Min Act: -0.1700
Data Index: 5306969 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.2688. Min Act: -0.1699
Data Index: 6470223 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.9563. Min Range: -16.9563
Max Act: 15.2688. Min Act: -0.1700
Data Index: 509182 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19