Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4508 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.6537. Min Act: -0.1700
Data Index: 5800475 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.4037. Min Act: -0.1700
Data Index: 7661402 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.3725. Min Act: -0.1700
Data Index: 6769018 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.3412. Min Act: -0.1700
Data Index: 4190019 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.2787. Min Act: -0.1700
Data Index: 7377452 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.2475. Min Act: -0.1700
Data Index: 7290488 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.2162. Min Act: -0.1700
Data Index: 1385587 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.2162. Min Act: -0.1700
Data Index: 5593926 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.2162. Min Act: -0.1700
Data Index: 3160733 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.2162. Min Act: -0.1700
Data Index: 8794908 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1850. Min Act: -0.1700
Data Index: 5154142 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1850. Min Act: -0.1700
Data Index: 2528419 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1850. Min Act: -0.1700
Data Index: 7661399 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1850. Min Act: -0.1700
Data Index: 331906 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 2385396 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 8488848 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 8488843 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 2686027 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 6488325 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6537. Min Range: -5.6537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 71675 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19