Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.2899. Min Act: -0.1700
Data Index: 245780 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.2587. Min Act: -0.1700
Data Index: 5566074 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.1649. Min Act: -0.1700
Data Index: 172133 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.1649. Min Act: -0.1700
Data Index: 7340276 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.1649. Min Act: -0.1700
Data Index: 1925442 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.1649. Min Act: -0.1700
Data Index: 4124251 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.1649. Min Act: -0.1700
Data Index: 4231493 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.1649. Min Act: -0.1700
Data Index: 4739089 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.1024. Min Act: -0.1700
Data Index: 6419052 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.0712. Min Act: -0.1700
Data Index: 7111967 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.0399. Min Act: -0.1700
Data Index: 6239838 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.0399. Min Act: -0.1700
Data Index: 3480491 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.0399. Min Act: -0.1700
Data Index: 5342101 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2899. Min Range: -7.2899
Max Act: 6.9774. Min Act: -0.1700
Data Index: 4596126 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2899. Min Range: -7.2899
Max Act: 6.9774. Min Act: -0.1700
Data Index: 1257249 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2899. Min Range: -7.2899
Max Act: 6.9774. Min Act: -0.1700
Data Index: 4841767 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2899. Min Range: -7.2899
Max Act: 7.0087. Min Act: -0.1700
Data Index: 268988 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2899. Min Range: -7.2899
Max Act: 6.9462. Min Act: -0.1700
Data Index: 470918 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2899. Min Range: -7.2899
Max Act: 6.9462. Min Act: -0.1700
Data Index: 2443016 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2899. Min Range: -7.2899
Max Act: 6.9462. Min Act: -0.1700
Data Index: 4112930 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19