Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3246. Min Range: -6.3246
Max Act: 6.2933. Min Act: -0.1700
Data Index: 5994290 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3246. Min Range: -6.3246
Max Act: 6.3246. Min Act: -0.1700
Data Index: 5876936 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.5746. Min Act: -0.1700
Data Index: 617057 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.5121. Min Act: -0.1700
Data Index: 1645612 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.5121. Min Act: -0.1700
Data Index: 5790369 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.4496. Min Act: -0.1700
Data Index: 3725608 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.4496. Min Act: -0.1700
Data Index: 7540589 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.4183. Min Act: -0.1700
Data Index: 4311807 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3871. Min Act: -0.1700
Data Index: 4217139 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3871. Min Act: -0.1700
Data Index: 3598144 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3558. Min Act: -0.1700
Data Index: 7101923 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3558. Min Act: -0.1700
Data Index: 316298 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.2933. Min Act: -0.1700
Data Index: 5584497 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3246. Min Act: -0.1700
Data Index: 1571218 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3246. Min Act: -0.1700
Data Index: 4002053 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3246. Min Act: -0.1700
Data Index: 585715 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.3246. Min Act: -0.1700
Data Index: 7101921 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.2621. Min Act: -0.1700
Data Index: 2002553 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.2933. Min Act: -0.1700
Data Index: 569713 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3246. Min Range: -6.3246
Max Act: 5.2933. Min Act: -0.1700
Data Index: 1099673 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19