Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0337. Min Range: -2.0337
Max Act: 2.0337. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0337. Min Range: -2.0337
Max Act: 1.2705. Min Act: -0.1700
Data Index: 230674 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0337. Min Range: -2.0337
Max Act: 1.4292. Min Act: -0.1700
Data Index: 7865669 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.7273. Min Act: -0.1700
Data Index: 4993227 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0337. Min Range: -2.0337
Max Act: 1.0335. Min Act: -0.1700
Data Index: 6555068 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.7027. Min Act: -0.1700
Data Index: 5320687 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.6864. Min Act: -0.1700
Data Index: 879507 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.6702. Min Act: -0.1700
Data Index: 1305906 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.6622. Min Act: -0.1700
Data Index: 2001387 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.7273. Min Act: -0.1698
Data Index: 7913476 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.5828. Min Act: -0.1700
Data Index: 8116505 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.5828. Min Act: -0.1697
Data Index: 167452 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.5595. Min Act: -0.1692
Data Index: 7588819 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.5060. Min Act: -0.1700
Data Index: 8752172 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.5060. Min Act: -0.1700
Data Index: 6262967 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.4910. Min Act: -0.1700
Data Index: 7235937 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.5060. Min Act: -0.1700
Data Index: 470877 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.4910. Min Act: -0.1700
Data Index: 7538897 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.4910. Min Act: -0.1700
Data Index: 3807053 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0337. Min Range: -2.0337
Max Act: 0.4910. Min Act: -0.1700
Data Index: 7685076 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19