Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.3549. Min Act: -0.1700
Data Index: 6316958 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.3549. Min Act: -0.1700
Data Index: 5790250 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.3861. Min Act: -0.1700
Data Index: 212957 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.3549. Min Act: -0.1700
Data Index: 2642525 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.3549. Min Act: -0.1700
Data Index: 1169378 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.3236. Min Act: -0.1700
Data Index: 5461262 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2299. Min Act: -0.1700
Data Index: 7247296 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2611. Min Act: -0.1700
Data Index: 2164378 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6264236 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2611. Min Act: -0.1700
Data Index: 7976496 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2299. Min Act: -0.1700
Data Index: 1170364 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2611. Min Act: -0.1700
Data Index: 7347002 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2299. Min Act: -0.1700
Data Index: 2976935 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2299. Min Act: -0.1700
Data Index: 923839 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2611. Min Act: -0.1700
Data Index: 1179440 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2299. Min Act: -0.1700
Data Index: 975649 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2299. Min Act: -0.1700
Data Index: 1305318 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2299. Min Act: -0.1700
Data Index: 4651608 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.1986. Min Act: -0.1700
Data Index: 2204775 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3861. Min Range: -5.3861
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6896781 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19