Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3868. Min Act: -0.1700
Data Index: 4096699 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3868. Min Act: -0.1700
Data Index: 5389433 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3556. Min Act: -0.1700
Data Index: 2160030 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3556. Min Act: -0.1700
Data Index: 3205764 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3243. Min Act: -0.1700
Data Index: 848092 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2931. Min Act: -0.1700
Data Index: 1484122 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3243. Min Act: -0.1700
Data Index: 5114778 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2931. Min Act: -0.1700
Data Index: 346663 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2931. Min Act: -0.1700
Data Index: 117274 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2931. Min Act: -0.1700
Data Index: 1185538 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 267833 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 346670 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 346660 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 346668 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 346661 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 141730 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 3461346 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1993. Min Act: -0.1700
Data Index: 2485697 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 2331731 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 733681 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19