Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.2982. Min Range: -19.2982
Max Act: 19.2982. Min Act: -0.1700
Data Index: 5304868 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.2982. Min Range: -19.2982
Max Act: 19.2982. Min Act: -0.1700
Data Index: 6630788 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.2982. Min Range: -19.2982
Max Act: 19.0482. Min Act: -0.1700
Data Index: 7512848 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.2982. Min Range: -19.2982
Max Act: 18.1732. Min Act: -0.1700
Data Index: 3996382 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.9232. Min Act: -0.1700
Data Index: 3996384 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.9232. Min Act: -0.1700
Data Index: 7999279 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.9232. Min Act: -0.1700
Data Index: 5524748 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.9232. Min Act: -0.1700
Data Index: 7999275 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.7982. Min Act: -0.1699
Data Index: 5842367 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.7982. Min Act: -0.1700
Data Index: 5842369 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.7982. Min Act: -0.1700
Data Index: 1909357 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.6732. Min Act: -0.1700
Data Index: 3756415 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.6732. Min Act: -0.1700
Data Index: 3756414 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.6732. Min Act: -0.1700
Data Index: 1329648 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.5482. Min Act: -0.1700
Data Index: 2134568 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.5482. Min Act: -0.1700
Data Index: 4864426 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.4232. Min Act: -0.1700
Data Index: 8645342 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.4232. Min Act: -0.1700
Data Index: 7609740 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.4232. Min Act: -0.1700
Data Index: 6462441 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.2982. Min Range: -19.2982
Max Act: 17.4232. Min Act: -0.1700
Data Index: 7306803 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19