Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0143. Min Range: -8.0143
Max Act: 8.0143. Min Act: -0.1700
Data Index: 5116929 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.5768. Min Act: -0.1700
Data Index: 2510289 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.5456. Min Act: -0.1700
Data Index: 6151847 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.3893. Min Act: -0.1700
Data Index: 5225143 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.2956. Min Act: -0.1700
Data Index: 8343627 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.2331. Min Act: -0.1700
Data Index: 1151381 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.2018. Min Act: -0.1700
Data Index: 5964155 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.1706. Min Act: -0.1700
Data Index: 4847266 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.1393. Min Act: -0.1700
Data Index: 4058396 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.1393. Min Act: -0.1700
Data Index: 7270738 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.0768. Min Act: -0.1700
Data Index: 8813375 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.0143. Min Act: -0.1700
Data Index: 6785394 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.0456. Min Act: -0.1700
Data Index: 3137755 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.0456. Min Act: -0.1700
Data Index: 2514888 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.0143. Min Act: -0.1700
Data Index: 1916972 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.0143. Min Act: -0.1700
Data Index: 3432531 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0143. Min Range: -8.0143
Max Act: 6.9831. Min Act: -0.1700
Data Index: 3311286 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0143. Min Range: -8.0143
Max Act: 6.9831. Min Act: -0.1700
Data Index: 8645735 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0143. Min Range: -8.0143
Max Act: 6.9518. Min Act: -0.1700
Data Index: 135849 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0143. Min Range: -8.0143
Max Act: 7.0143. Min Act: -0.1700
Data Index: 5443644 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19