Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.4363. Min Act: -0.1700
Data Index: 5236000 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.4363. Min Act: -0.1700
Data Index: 6520538 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.3738. Min Act: -0.1700
Data Index: 5095992 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.2801. Min Act: -0.1700
Data Index: 8150172 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.2488. Min Act: -0.1700
Data Index: 2005959 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.2488. Min Act: -0.1700
Data Index: 160392 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.2176. Min Act: -0.1700
Data Index: 5266765 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.2176. Min Act: -0.1700
Data Index: 2568943 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.2176. Min Act: -0.1700
Data Index: 1298283 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1863. Min Act: -0.1700
Data Index: 3486098 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1551. Min Act: -0.1700
Data Index: 5388986 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1863. Min Act: -0.1700
Data Index: 3336476 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1551. Min Act: -0.1700
Data Index: 2197946 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1238. Min Act: -0.1700
Data Index: 5076003 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1551. Min Act: -0.1700
Data Index: 2844797 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1551. Min Act: -0.1700
Data Index: 7206288 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1551. Min Act: -0.1700
Data Index: 3492301 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1238. Min Act: -0.1700
Data Index: 440821 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.0926. Min Act: -0.1700
Data Index: 4727940 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4363. Min Range: -6.4363
Max Act: 6.1238. Min Act: -0.1700
Data Index: 1843565 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19