Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.3219. Min Act: -0.1700
Data Index: 4951904 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.3062. Min Act: -0.1700
Data Index: 6524477 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.3062. Min Act: -0.1700
Data Index: 2906844 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.3062. Min Act: -0.1700
Data Index: 7480141 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2591. Min Act: -0.1700
Data Index: 4001891 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2277. Min Act: -0.1700
Data Index: 8069902 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2748. Min Act: -0.1700
Data Index: 3164224 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2120. Min Act: -0.1700
Data Index: 8029014 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2591. Min Act: -0.1700
Data Index: 8167876 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2434. Min Act: -0.1700
Data Index: 6536704 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.1962. Min Act: -0.1700
Data Index: 8570352 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2277. Min Act: -0.1700
Data Index: 2966598 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2120. Min Act: -0.1700
Data Index: 3165770 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.1962. Min Act: -0.1700
Data Index: 2441958 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.1805. Min Act: -0.1700
Data Index: 8195125 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.1490. Min Act: -0.1700
Data Index: 4970935 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.2120. Min Act: -0.1700
Data Index: 590649 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.1648. Min Act: -0.1700
Data Index: 4214049 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.1648. Min Act: -0.1700
Data Index: 3461886 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3219. Min Range: -3.3219
Max Act: 3.1490. Min Act: -0.1700
Data Index: 1311968 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19