Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.3035. Min Act: -0.1700
Data Index: 516130 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.1785. Min Act: -0.1700
Data Index: 935176 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.1473. Min Act: -0.1700
Data Index: 3984548 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.0535. Min Act: -0.1700
Data Index: 7906488 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.0535. Min Act: -0.1700
Data Index: 3406678 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.0223. Min Act: -0.1700
Data Index: 170445 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9910. Min Act: -0.1700
Data Index: 7388433 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9598. Min Act: -0.1700
Data Index: 6994970 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8973. Min Act: -0.1700
Data Index: 2349275 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8973. Min Act: -0.1700
Data Index: 7127734 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8660. Min Act: -0.1700
Data Index: 13451 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1110060 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8348. Min Act: -0.1700
Data Index: 659387 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8348. Min Act: -0.1700
Data Index: 6767396 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8035. Min Act: -0.1700
Data Index: 630677 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.7723. Min Act: -0.1700
Data Index: 346162 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8035. Min Act: -0.1700
Data Index: 2596908 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8035. Min Act: -0.1700
Data Index: 5511100 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8035. Min Act: -0.1700
Data Index: 1248814 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.7723. Min Act: -0.1700
Data Index: 2609035 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19