Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.9567. Min Act: -0.1700
Data Index: 7837664 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.8317. Min Act: -0.1700
Data Index: 2142014 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.8004. Min Act: -0.1700
Data Index: 2658553 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.8004. Min Act: -0.1700
Data Index: 5566107 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7692. Min Act: -0.1700
Data Index: 216857 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7692. Min Act: -0.1700
Data Index: 3320946 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7692. Min Act: -0.1700
Data Index: 6078569 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7692. Min Act: -0.1700
Data Index: 4519277 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 3368345 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 8093651 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 1401047 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 5779323 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 6835449 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 5606925 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 8131600 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7379. Min Act: -0.1700
Data Index: 6430628 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7067. Min Act: -0.1700
Data Index: 79567 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7067. Min Act: -0.1700
Data Index: 4002921 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.7067. Min Act: -0.1700
Data Index: 5684660 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9567. Min Range: -4.9567
Max Act: 4.6754. Min Act: -0.1700
Data Index: 7964630 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19