Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2473 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.7678. Min Act: -0.1700
Data Index: 8414149 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.7366. Min Act: -0.1700
Data Index: 6994004 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.6428. Min Act: -0.1700
Data Index: 8815964 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.6428. Min Act: -0.1700
Data Index: 839004 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.6116. Min Act: -0.1700
Data Index: 2479586 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.6428. Min Act: -0.1700
Data Index: 500485 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.6116. Min Act: -0.1700
Data Index: 2844451 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.6428. Min Act: -0.1700
Data Index: 1064174 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5803. Min Act: -0.1700
Data Index: 6569822 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5803. Min Act: -0.1700
Data Index: 2518418 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5803. Min Act: -0.1700
Data Index: 6764343 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5803. Min Act: -0.1700
Data Index: 5867883 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5491. Min Act: -0.1700
Data Index: 8231 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5491. Min Act: -0.1700
Data Index: 3245402 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5491. Min Act: -0.1700
Data Index: 6901589 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5491. Min Act: -0.1700
Data Index: 220613 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5491. Min Act: -0.1700
Data Index: 4556139 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5178. Min Act: -0.1700
Data Index: 640645 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5178. Min Act: -0.1700
Data Index: 301873 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7678. Min Range: -4.7678
Max Act: 4.5178. Min Act: -0.1700
Data Index: 7294137 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19