Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.6218. Min Act: -0.1700
Data Index: 1322092 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.5432. Min Act: -0.1700
Data Index: 3531471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.5256. Min Act: -0.1700
Data Index: 2848992 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4905. Min Act: -0.1626
Data Index: 5210131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4905. Min Act: -0.1700
Data Index: 6154741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4905. Min Act: -0.1690
Data Index: 7929659 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4817. Min Act: -0.1700
Data Index: 5267962 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4730. Min Act: -0.1700
Data Index: 2912832 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4730. Min Act: -0.1689
Data Index: 3160211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4642. Min Act: -0.1700
Data Index: 3637195 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4554. Min Act: -0.1645
Data Index: 7169969 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4466. Min Act: -0.1699
Data Index: 323849 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4466. Min Act: -0.1700
Data Index: 1763014 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4466. Min Act: -0.1697
Data Index: 3705401 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4466. Min Act: -0.1700
Data Index: 1022901 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4554. Min Act: -0.1700
Data Index: 3253926 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4378. Min Act: -0.1700
Data Index: 8271044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4378. Min Act: -0.1700
Data Index: 1279680 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4466. Min Act: -0.1690
Data Index: 1006462 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6218. Min Range: -1.6218
Max Act: 1.4290. Min Act: -0.1700
Data Index: 2040931 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19