Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.6231. Min Act: -0.1700
Data Index: 4593271 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.6231. Min Act: -0.1700
Data Index: 8547384 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.6231. Min Act: -0.1700
Data Index: 5802740 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.6231. Min Act: -0.1700
Data Index: 8547383 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.5606. Min Act: -0.1700
Data Index: 5802741 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.5294. Min Act: -0.1700
Data Index: 1574749 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.3731. Min Act: -0.1700
Data Index: 8466016 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.3106. Min Act: -0.1700
Data Index: 748268 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.3106. Min Act: -0.1700
Data Index: 6164178 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.2481. Min Act: -0.1700
Data Index: 4553729 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.1856. Min Act: -0.1700
Data Index: 2205191 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.1856. Min Act: -0.1700
Data Index: 1574748 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.0294. Min Act: -0.1700
Data Index: 7035469 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6231. Min Range: -7.6231
Max Act: 7.0294. Min Act: -0.1700
Data Index: 4084391 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6231. Min Range: -7.6231
Max Act: 6.9356. Min Act: -0.1700
Data Index: 4039902 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6231. Min Range: -7.6231
Max Act: 6.9669. Min Act: -0.1700
Data Index: 476671 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6231. Min Range: -7.6231
Max Act: 6.8731. Min Act: -0.1700
Data Index: 3113780 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6231. Min Range: -7.6231
Max Act: 6.8419. Min Act: -0.1700
Data Index: 4465428 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6231. Min Range: -7.6231
Max Act: 6.8419. Min Act: -0.1700
Data Index: 2415651 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6231. Min Range: -7.6231
Max Act: 6.7794. Min Act: -0.1700
Data Index: 500872 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19