Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 113 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.5666. Min Act: -0.1700
Data Index: 4874836 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.4416. Min Act: -0.1700
Data Index: 6120159 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.3166. Min Act: -0.1700
Data Index: 8738565 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.2541. Min Act: -0.1700
Data Index: 2060521 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.0666. Min Act: -0.1700
Data Index: 6810925 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.0666. Min Act: -0.1700
Data Index: 7451206 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.0666. Min Act: -0.1700
Data Index: 5875892 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.0666. Min Act: -0.1700
Data Index: 8356174 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.1291. Min Act: -0.1700
Data Index: 1497151 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.0041. Min Act: -0.1700
Data Index: 7605230 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.9416. Min Act: -0.1700
Data Index: 3699528 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.9416. Min Act: -0.1700
Data Index: 3379009 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.8791. Min Act: -0.1700
Data Index: 1166205 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.0041. Min Act: -0.1700
Data Index: 249794 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.8791. Min Act: -0.1700
Data Index: 2040429 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.9416. Min Act: -0.1700
Data Index: 4931076 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5666. Min Range: -8.5666
Max Act: 8.0041. Min Act: -0.1700
Data Index: 2473121 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.9416. Min Act: -0.1700
Data Index: 3167534 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.8166. Min Act: -0.1700
Data Index: 857171 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5666. Min Range: -8.5666
Max Act: 7.8791. Min Act: -0.1700
Data Index: 3342936 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19