Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6387 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.5583. Min Act: -0.1700
Data Index: 2465204 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.3232. Min Act: -0.1700
Data Index: 7927295 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.3075. Min Act: -0.1700
Data Index: 2156187 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.2604. Min Act: -0.1700
Data Index: 8459462 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.2447. Min Act: -0.1700
Data Index: 4354291 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.2604. Min Act: -0.1700
Data Index: 3770852 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1818. Min Act: -0.1700
Data Index: 5161939 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1975. Min Act: -0.1700
Data Index: 1308528 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1818. Min Act: -0.1700
Data Index: 5358126 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1661. Min Act: -0.1700
Data Index: 4952650 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1503. Min Act: -0.1700
Data Index: 8161501 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1346. Min Act: -0.1700
Data Index: 3012207 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1346. Min Act: -0.1700
Data Index: 2295587 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1346. Min Act: -0.1700
Data Index: 2116854 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1503. Min Act: -0.1700
Data Index: 8701024 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1188. Min Act: -0.1700
Data Index: 8467442 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1188. Min Act: -0.1700
Data Index: 1446912 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1031. Min Act: -0.1700
Data Index: 4800181 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1188. Min Act: -0.1700
Data Index: 3167063 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5583. Min Range: -3.5583
Max Act: 3.1188. Min Act: -0.1700
Data Index: 1911504 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19