Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.6553. Min Act: -0.1700
Data Index: 6637135 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.5928. Min Act: -0.1700
Data Index: 2411267 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.6241. Min Act: -0.1700
Data Index: 7448468 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.5928. Min Act: -0.1700
Data Index: 7304508 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.5928. Min Act: -0.1700
Data Index: 124283 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.4366. Min Act: -0.1700
Data Index: 3153332 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.4678. Min Act: -0.1700
Data Index: 5818600 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.4053. Min Act: -0.1700
Data Index: 8807093 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.4053. Min Act: -0.1700
Data Index: 4451218 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.3741. Min Act: -0.1700
Data Index: 7958295 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.3741. Min Act: -0.1700
Data Index: 4856797 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.3741. Min Act: -0.1700
Data Index: 1873206 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.3741. Min Act: -0.1700
Data Index: 4446525 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.3428. Min Act: -0.1700
Data Index: 1012620 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.3116. Min Act: -0.1700
Data Index: 5469826 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.3116. Min Act: -0.1700
Data Index: 480202 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.2803. Min Act: -0.1700
Data Index: 2989869 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.2178. Min Act: -0.1700
Data Index: 5459955 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.2803. Min Act: -0.1700
Data Index: 1183639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6553. Min Range: -7.6553
Max Act: 7.2491. Min Act: -0.1700
Data Index: 1904243 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19