Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1844 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.3351. Min Act: -0.1700
Data Index: 2267023 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.3351. Min Act: -0.1700
Data Index: 5411439 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.3039. Min Act: -0.1700
Data Index: 6136784 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.2726. Min Act: -0.1700
Data Index: 2333516 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.2726. Min Act: -0.1700
Data Index: 6561464 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.2726. Min Act: -0.1700
Data Index: 1435720 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.2414. Min Act: -0.1700
Data Index: 4686247 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.2101. Min Act: -0.1700
Data Index: 7292009 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1476. Min Act: -0.1700
Data Index: 3285721 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1476. Min Act: -0.1700
Data Index: 8326721 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1476. Min Act: -0.1700
Data Index: 3445487 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1164. Min Act: -0.1700
Data Index: 8379661 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1164. Min Act: -0.1700
Data Index: 2479288 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1164. Min Act: -0.1700
Data Index: 7862375 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1164. Min Act: -0.1700
Data Index: 6609461 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.1164. Min Act: -0.1700
Data Index: 5284803 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.0851. Min Act: -0.1700
Data Index: 749826 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.0539. Min Act: -0.1700
Data Index: 8559709 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.0539. Min Act: -0.1700
Data Index: 1556068 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3351. Min Range: -7.3351
Max Act: 7.0539. Min Act: -0.1700
Data Index: 5056103 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19