Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.6647. Min Act: -0.1700
Data Index: 2430566 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.5710. Min Act: -0.1700
Data Index: 8395323 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.5710. Min Act: -0.1700
Data Index: 7398849 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.5397. Min Act: -0.1700
Data Index: 8395320 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 7612561 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.5085. Min Act: -0.1700
Data Index: 3305137 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 4803585 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 5081920 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 7730343 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 3769425 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4459. Min Act: -0.1700
Data Index: 3802755 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 2430565 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 3207066 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 134352 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 2786514 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4459. Min Act: -0.1700
Data Index: 8717249 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4772. Min Act: -0.1700
Data Index: 2973465 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4459. Min Act: -0.1700
Data Index: 2989371 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4459. Min Act: -0.1700
Data Index: 2786513 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6647. Min Range: -4.6647
Max Act: 4.4459. Min Act: -0.1700
Data Index: 6050246 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19