Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1518 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.8635. Min Act: -0.1700
Data Index: 3623793 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.7385. Min Act: -0.1700
Data Index: 2005419 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.5510. Min Act: -0.1700
Data Index: 4239164 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.4573. Min Act: -0.1700
Data Index: 8645552 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.4573. Min Act: -0.1700
Data Index: 5082825 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.4260. Min Act: -0.1700
Data Index: 137569 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3635. Min Act: -0.1700
Data Index: 3181555 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3635. Min Act: -0.1700
Data Index: 3861353 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3635. Min Act: -0.1700
Data Index: 2900494 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3635. Min Act: -0.1700
Data Index: 1850386 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3323. Min Act: -0.1700
Data Index: 5286604 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3323. Min Act: -0.1700
Data Index: 5565328 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.2697. Min Act: -0.1700
Data Index: 5841157 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 3923802 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.2697. Min Act: -0.1700
Data Index: 3646763 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.2697. Min Act: -0.1700
Data Index: 3717648 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 2819877 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.2697. Min Act: -0.1700
Data Index: 8376428 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.2385. Min Act: -0.1700
Data Index: 560992 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8635. Min Range: -4.8635
Max Act: 4.2385. Min Act: -0.1700
Data Index: 7480885 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19