Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 10.2265. Min Range: -10.2265
Max Act: 10.2265. Min Act: -0.1700
Data Index: 5416462 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2265. Min Range: -10.2265
Max Act: 10.2265. Min Act: -0.1700
Data Index: 2220158 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2265. Min Range: -10.2265
Max Act: 10.1015. Min Act: -0.1700
Data Index: 6198178 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.7265. Min Act: -0.1700
Data Index: 4501609 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.6640. Min Act: -0.1700
Data Index: 3139255 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.6640. Min Act: -0.1700
Data Index: 8220706 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.5390. Min Act: -0.1700
Data Index: 1084571 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.6015. Min Act: -0.1700
Data Index: 5307486 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.5390. Min Act: -0.1699
Data Index: 2398368 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.5390. Min Act: -0.1700
Data Index: 4023567 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.5390. Min Act: -0.1700
Data Index: 5144159 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.6015. Min Act: -0.1700
Data Index: 4124952 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.5390. Min Act: -0.1700
Data Index: 6704085 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.4140. Min Act: -0.1700
Data Index: 4680352 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.2265. Min Act: -0.1700
Data Index: 1084595 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.2890. Min Act: -0.1700
Data Index: 1337981 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.2890. Min Act: -0.1700
Data Index: 4893711 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.2265. Min Act: -0.1700
Data Index: 4300007 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.2265. Min Act: -0.1700
Data Index: 2596530 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2265. Min Range: -10.2265
Max Act: 9.2265. Min Act: -0.1699
Data Index: 8129004 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19