Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2516 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.9477. Min Act: -0.1700
Data Index: 6981876 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.8227. Min Act: -0.1700
Data Index: 1688297 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.5415. Min Act: -0.1700
Data Index: 4454640 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.4790. Min Act: -0.1700
Data Index: 3533667 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.4790. Min Act: -0.1700
Data Index: 2603860 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.3852. Min Act: -0.1700
Data Index: 884488 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.3540. Min Act: -0.1700
Data Index: 8443794 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.3227. Min Act: -0.1700
Data Index: 1324110 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.2915. Min Act: -0.1700
Data Index: 4001367 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.2290. Min Act: -0.1700
Data Index: 1440957 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1977. Min Act: -0.1700
Data Index: 6334858 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1352. Min Act: -0.1700
Data Index: 4504182 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1665. Min Act: -0.1700
Data Index: 3096226 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1977. Min Act: -0.1700
Data Index: 373225 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1665. Min Act: -0.1700
Data Index: 4789706 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1352. Min Act: -0.1700
Data Index: 3135791 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1040. Min Act: -0.1700
Data Index: 3279724 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1352. Min Act: -0.1700
Data Index: 3667029 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1352. Min Act: -0.1700
Data Index: 6433231 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9477. Min Range: -6.9477
Max Act: 6.1040. Min Act: -0.1700
Data Index: 907001 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19