Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4675 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1359. Min Range: -7.1359
Max Act: 7.1359. Min Act: -0.1700
Data Index: 6809000 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.9484. Min Act: -0.1700
Data Index: 6808999 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.9171. Min Act: -0.1700
Data Index: 912226 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.8546. Min Act: -0.1700
Data Index: 4767229 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.8234. Min Act: -0.1700
Data Index: 5800227 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.8234. Min Act: -0.1700
Data Index: 5621878 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.8234. Min Act: -0.1700
Data Index: 2576685 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.7296. Min Act: -0.1700
Data Index: 8741806 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.7296. Min Act: -0.1700
Data Index: 2790950 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6984. Min Act: -0.1700
Data Index: 1744449 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6984. Min Act: -0.1700
Data Index: 270343 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6984. Min Act: -0.1700
Data Index: 3382375 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6984. Min Act: -0.1700
Data Index: 4425507 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6671. Min Act: -0.1700
Data Index: 7314550 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6671. Min Act: -0.1700
Data Index: 3528192 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6984. Min Act: -0.1700
Data Index: 5048383 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6671. Min Act: -0.1700
Data Index: 2217902 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6671. Min Act: -0.1700
Data Index: 1408586 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6359. Min Act: -0.1700
Data Index: 2965380 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1359. Min Range: -7.1359
Max Act: 6.6046. Min Act: -0.1700
Data Index: 2727565 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19