Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 235 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3301. Min Range: -8.3301
Max Act: 8.3301. Min Act: -0.1700
Data Index: 3768927 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3301. Min Range: -8.3301
Max Act: 8.1426. Min Act: -0.1700
Data Index: 4314419 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3301. Min Range: -8.3301
Max Act: 8.0489. Min Act: -0.1700
Data Index: 692405 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3301. Min Range: -8.3301
Max Act: 8.0176. Min Act: -0.1700
Data Index: 7942376 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3301. Min Range: -8.3301
Max Act: 8.0801. Min Act: -0.1700
Data Index: 2362071 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.9551. Min Act: -0.1700
Data Index: 4590043 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.9864. Min Act: -0.1700
Data Index: 2225323 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.9551. Min Act: -0.1700
Data Index: 6236144 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.8926. Min Act: -0.1700
Data Index: 8058801 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.8926. Min Act: -0.1700
Data Index: 8010101 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.8926. Min Act: -0.1700
Data Index: 6397952 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.8301. Min Act: -0.1700
Data Index: 2288323 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7676. Min Act: -0.1700
Data Index: 262653 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7989. Min Act: -0.1700
Data Index: 1620093 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7676. Min Act: -0.1700
Data Index: 1128303 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7676. Min Act: -0.1700
Data Index: 7719031 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7676. Min Act: -0.1700
Data Index: 5728983 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7364. Min Act: -0.1700
Data Index: 4213057 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7364. Min Act: -0.1700
Data Index: 3597569 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3301. Min Range: -8.3301
Max Act: 7.7364. Min Act: -0.1700
Data Index: 7517330 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19