Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.7498. Min Act: -0.1700
Data Index: 6643782 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.6248. Min Act: -0.1700
Data Index: 5694545 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.5623. Min Act: -0.1700
Data Index: 1598478 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.4998. Min Act: -0.1700
Data Index: 2871427 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3748. Min Act: -0.1700
Data Index: 2357333 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.4998. Min Act: -0.1700
Data Index: 8070209 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3748. Min Act: -0.1700
Data Index: 7222721 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3123. Min Act: -0.1700
Data Index: 2568500 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3123. Min Act: -0.1700
Data Index: 8377530 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3123. Min Act: -0.1700
Data Index: 5296983 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.2498. Min Act: -0.1700
Data Index: 5610716 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3123. Min Act: -0.1700
Data Index: 7431083 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3123. Min Act: -0.1700
Data Index: 3526381 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.3123. Min Act: -0.1700
Data Index: 8519021 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.2498. Min Act: -0.1700
Data Index: 7873783 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.2498. Min Act: -0.1700
Data Index: 7503996 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.2498. Min Act: -0.1700
Data Index: 8087657 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.2498. Min Act: -0.1700
Data Index: 832550 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.2498. Min Act: -0.1700
Data Index: 3998603 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7498. Min Range: -9.7498
Max Act: 9.2498. Min Act: -0.1700
Data Index: 519213 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19