Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4337 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.6385. Min Act: -0.1700
Data Index: 2372456 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.6385. Min Act: -0.1700
Data Index: 8552472 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.5135. Min Act: -0.1700
Data Index: 43560 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.5448. Min Act: -0.1700
Data Index: 5852693 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.5135. Min Act: -0.1700
Data Index: 5466820 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.4198. Min Act: -0.1700
Data Index: 8759056 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.4198. Min Act: -0.1700
Data Index: 1840032 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.3885. Min Act: -0.1700
Data Index: 5710271 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.3885. Min Act: -0.1700
Data Index: 6572324 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.3573. Min Act: -0.1700
Data Index: 7576607 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.3260. Min Act: -0.1700
Data Index: 169115 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.3260. Min Act: -0.1700
Data Index: 7107770 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.3260. Min Act: -0.1700
Data Index: 1562628 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.2948. Min Act: -0.1700
Data Index: 6281085 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.2948. Min Act: -0.1700
Data Index: 3546133 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.2948. Min Act: -0.1700
Data Index: 4826781 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.2635. Min Act: -0.1700
Data Index: 6246961 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.2635. Min Act: -0.1700
Data Index: 5226055 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.2635. Min Act: -0.1700
Data Index: 3020218 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6385. Min Range: -5.6385
Max Act: 5.2635. Min Act: -0.1700
Data Index: 8679979 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19