Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1112 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.6454. Min Act: -0.1700
Data Index: 6486498 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.6141. Min Act: -0.1700
Data Index: 4162329 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.5829. Min Act: -0.1700
Data Index: 7382189 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.5204. Min Act: -0.1700
Data Index: 4118452 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.5204. Min Act: -0.1700
Data Index: 384832 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4891. Min Act: -0.1700
Data Index: 8664489 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4579. Min Act: -0.1700
Data Index: 2370466 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4891. Min Act: -0.1700
Data Index: 8310816 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4579. Min Act: -0.1700
Data Index: 3856651 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4579. Min Act: -0.1700
Data Index: 903030 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4579. Min Act: -0.1700
Data Index: 664677 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.3954. Min Act: -0.1700
Data Index: 2200995 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.3954. Min Act: -0.1700
Data Index: 2318920 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4266. Min Act: -0.1700
Data Index: 5237859 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4266. Min Act: -0.1700
Data Index: 5083438 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.3954. Min Act: -0.1700
Data Index: 924503 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.3954. Min Act: -0.1700
Data Index: 536396 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4266. Min Act: -0.1700
Data Index: 3690775 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.3954. Min Act: -0.1700
Data Index: 2841305 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6454. Min Range: -7.6454
Max Act: 7.4266. Min Act: -0.1700
Data Index: 5615823 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19