Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.6104. Min Act: -0.1700
Data Index: 5548723 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.6417. Min Act: -0.1700
Data Index: 2098755 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.6417. Min Act: -0.1700
Data Index: 4392751 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.5792. Min Act: -0.1700
Data Index: 6395651 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.5479. Min Act: -0.1700
Data Index: 453045 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.5479. Min Act: -0.1700
Data Index: 8090146 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4854. Min Act: -0.1700
Data Index: 4054724 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4854. Min Act: -0.1700
Data Index: 6893218 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4229. Min Act: -0.1700
Data Index: 1173373 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4542. Min Act: -0.1700
Data Index: 4006293 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4542. Min Act: -0.1700
Data Index: 4306478 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4542. Min Act: -0.1700
Data Index: 8176549 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4542. Min Act: -0.1700
Data Index: 6717017 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4542. Min Act: -0.1700
Data Index: 210412 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4542. Min Act: -0.1700
Data Index: 7095868 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4229. Min Act: -0.1700
Data Index: 7458150 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4542. Min Act: -0.1700
Data Index: 6968002 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.4229. Min Act: -0.1700
Data Index: 109509 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.3917. Min Act: -0.1700
Data Index: 7229713 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6417. Min Range: -5.6417
Max Act: 5.3917. Min Act: -0.1700
Data Index: 5947544 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19