Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.8069. Min Act: -0.1700
Data Index: 3277470 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.6819. Min Act: -0.1700
Data Index: 8178022 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.4944. Min Act: -0.1700
Data Index: 1502851 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.4319. Min Act: -0.1700
Data Index: 4959285 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.4319. Min Act: -0.1700
Data Index: 7784942 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3694. Min Act: -0.1700
Data Index: 2054370 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3694. Min Act: -0.1700
Data Index: 8452691 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.2444. Min Act: -0.1700
Data Index: 8744283 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3069. Min Act: -0.1700
Data Index: 65647 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.2444. Min Act: -0.1700
Data Index: 1506847 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3069. Min Act: -0.1700
Data Index: 5825374 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3069. Min Act: -0.1700
Data Index: 4341421 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3069. Min Act: -0.1699
Data Index: 5243053 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3069. Min Act: -0.1700
Data Index: 736984 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3069. Min Act: -0.1700
Data Index: 5354795 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.3069. Min Act: -0.1700
Data Index: 5616304 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.2444. Min Act: -0.1700
Data Index: 6788370 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.2444. Min Act: -0.1700
Data Index: 4319225 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.2444. Min Act: -0.1700
Data Index: 5319739 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8069. Min Range: -8.8069
Max Act: 8.2444. Min Act: -0.1700
Data Index: 4601537 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19