Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4515 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.6977. Min Act: -0.1667
Data Index: 4371587 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.6630. Min Act: -0.1700
Data Index: 5709353 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.6630. Min Act: -0.1700
Data Index: 6525101 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.6107. Min Act: -0.1700
Data Index: 6525094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5933. Min Act: -0.1688
Data Index: 4133583 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5758. Min Act: -0.1621
Data Index: 3437125 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5845. Min Act: -0.1678
Data Index: 8183459 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5758. Min Act: -0.1700
Data Index: 6525117 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5845. Min Act: -0.1547
Data Index: 2543118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5758. Min Act: -0.1700
Data Index: 6525108 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5670. Min Act: -0.1700
Data Index: 6525096 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5758. Min Act: -0.1700
Data Index: 5709358 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5670. Min Act: -0.1700
Data Index: 5709355 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5670. Min Act: -0.1700
Data Index: 4334337 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5408. Min Act: -0.1686
Data Index: 8369893 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5408. Min Act: -0.1700
Data Index: 3867633 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5320. Min Act: -0.1700
Data Index: 4206998 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5320. Min Act: -0.1686
Data Index: 390406 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5232. Min Act: -0.1681
Data Index: 7627201 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6977. Min Range: -1.6977
Max Act: 1.5320. Min Act: -0.1700
Data Index: 5636011 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19