Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.8478. Min Act: -0.1700
Data Index: 3712749 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.8166. Min Act: -0.1700
Data Index: 129997 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.7853. Min Act: -0.1700
Data Index: 4096206 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.7853. Min Act: -0.1700
Data Index: 1818151 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6916. Min Act: -0.1700
Data Index: 5284341 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6603. Min Act: -0.1700
Data Index: 2207943 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6916. Min Act: -0.1700
Data Index: 8345876 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6603. Min Act: -0.1700
Data Index: 7027841 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6603. Min Act: -0.1700
Data Index: 8039969 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6603. Min Act: -0.1700
Data Index: 307000 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6291. Min Act: -0.1700
Data Index: 295206 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6291. Min Act: -0.1700
Data Index: 516823 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6291. Min Act: -0.1700
Data Index: 3751706 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.6291. Min Act: -0.1700
Data Index: 2687190 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.5978. Min Act: -0.1700
Data Index: 5558795 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.5978. Min Act: -0.1700
Data Index: 8345878 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.5666. Min Act: -0.1700
Data Index: 3665839 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.5666. Min Act: -0.1700
Data Index: 3114260 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.5666. Min Act: -0.1700
Data Index: 1922819 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8478. Min Range: -5.8478
Max Act: 5.5666. Min Act: -0.1700
Data Index: 1756579 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19