Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5964 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.6570. Min Act: -0.1700
Data Index: 4334464 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.5945. Min Act: -0.1700
Data Index: 8489410 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.4695. Min Act: -0.1700
Data Index: 5160094 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.5320. Min Act: -0.1700
Data Index: 5197305 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.4695. Min Act: -0.1700
Data Index: 4506845 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.4695. Min Act: -0.1700
Data Index: 5530237 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.4070. Min Act: -0.1700
Data Index: 6565286 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.4070. Min Act: -0.1700
Data Index: 734666 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.4070. Min Act: -0.1700
Data Index: 2974642 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.3445. Min Act: -0.1700
Data Index: 2691511 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.4070. Min Act: -0.1700
Data Index: 365728 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.3445. Min Act: -0.1700
Data Index: 4263998 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.2820. Min Act: -0.1700
Data Index: 4517334 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.2820. Min Act: -0.1700
Data Index: 1767998 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.3445. Min Act: -0.1700
Data Index: 1451536 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.2508. Min Act: -0.1700
Data Index: 3349036 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.2820. Min Act: -0.1700
Data Index: 2536636 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.2820. Min Act: -0.1700
Data Index: 2614760 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.2820. Min Act: -0.1700
Data Index: 557453 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6570. Min Range: -7.6570
Max Act: 7.2508. Min Act: -0.1700
Data Index: 4008729 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19