Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0590. Min Range: -4.0590
Max Act: 4.0590. Min Act: -0.1700
Data Index: 7358154 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9652. Min Act: -0.1700
Data Index: 2450585 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9340. Min Act: -0.1700
Data Index: 5686942 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9340. Min Act: -0.1700
Data Index: 8423582 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9027. Min Act: -0.1700
Data Index: 5898012 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9027. Min Act: -0.1700
Data Index: 6731751 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8714. Min Act: -0.1700
Data Index: 5666564 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 3041691 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8714. Min Act: -0.1700
Data Index: 3656400 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 5491752 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 1167191 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8714. Min Act: -0.1700
Data Index: 4620555 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 455690 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 995602 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8089. Min Act: -0.1700
Data Index: 5869077 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.7776. Min Act: -0.1700
Data Index: 6493973 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 2822452 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8089. Min Act: -0.1700
Data Index: 2117683 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.7932. Min Act: -0.1700
Data Index: 919582 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8089. Min Act: -0.1700
Data Index: 2031324 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19