Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5582 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.8269. Min Act: -0.1700
Data Index: 4528004 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.8269. Min Act: -0.1700
Data Index: 289861 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.7332. Min Act: -0.1700
Data Index: 4344803 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.7332. Min Act: -0.1700
Data Index: 8314643 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.7019. Min Act: -0.1700
Data Index: 3172571 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.6707. Min Act: -0.1700
Data Index: 4425811 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.6707. Min Act: -0.1700
Data Index: 4900276 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.6394. Min Act: -0.1700
Data Index: 7404554 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.6082. Min Act: -0.1700
Data Index: 2848886 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.6082. Min Act: -0.1700
Data Index: 88282 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.5769. Min Act: -0.1700
Data Index: 8538240 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.5769. Min Act: -0.1700
Data Index: 4508300 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.5457. Min Act: -0.1700
Data Index: 215268 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.5457. Min Act: -0.1700
Data Index: 430491 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.5457. Min Act: -0.1700
Data Index: 2861701 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.5457. Min Act: -0.1700
Data Index: 2921046 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.5144. Min Act: -0.1700
Data Index: 4778633 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.4519. Min Act: -0.1700
Data Index: 748369 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.4519. Min Act: -0.1700
Data Index: 2955790 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8269. Min Range: -4.8269
Max Act: 4.4519. Min Act: -0.1700
Data Index: 1718501 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19