Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2207. Min Range: -8.2207
Max Act: 8.2207. Min Act: -0.1700
Data Index: 3352648 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.6895. Min Act: -0.1700
Data Index: 8462533 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.4395. Min Act: -0.1700
Data Index: 7446929 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.3145. Min Act: -0.1700
Data Index: 3956028 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.2832. Min Act: -0.1700
Data Index: 703454 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.2207. Min Act: -0.1700
Data Index: 561322 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.2207. Min Act: -0.1700
Data Index: 8005729 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1895. Min Act: -0.1700
Data Index: 8677309 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1895. Min Act: -0.1700
Data Index: 4989651 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 774054 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 6817412 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 6373411 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 4696284 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 2737873 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 5957603 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.0957. Min Act: -0.1700
Data Index: 4358498 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.0645. Min Act: -0.1700
Data Index: 8005731 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 1447216 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.0957. Min Act: -0.1700
Data Index: 1099018 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2207. Min Range: -8.2207
Max Act: 7.0957. Min Act: -0.1700
Data Index: 5517113 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19