Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0317. Min Range: -8.0317
Max Act: 8.0317. Min Act: -0.1700
Data Index: 901888 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.8754. Min Act: -0.1700
Data Index: 3915662 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.7817. Min Act: -0.1700
Data Index: 2309878 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.7192. Min Act: -0.1700
Data Index: 1122152 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.6567. Min Act: -0.1700
Data Index: 683759 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.6567. Min Act: -0.1700
Data Index: 4796096 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5942. Min Act: -0.1700
Data Index: 7048670 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5629. Min Act: -0.1700
Data Index: 33034 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5629. Min Act: -0.1700
Data Index: 1050750 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5629. Min Act: -0.1700
Data Index: 3223733 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5942. Min Act: -0.1700
Data Index: 2145290 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5317. Min Act: -0.1700
Data Index: 5199872 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5317. Min Act: -0.1700
Data Index: 5505442 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5004. Min Act: -0.1700
Data Index: 4130261 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.4692. Min Act: -0.1700
Data Index: 4837050 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.5004. Min Act: -0.1700
Data Index: 7488327 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.4692. Min Act: -0.1700
Data Index: 5639212 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.4379. Min Act: -0.1700
Data Index: 2214099 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.4067. Min Act: -0.1700
Data Index: 5028996 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0317. Min Range: -8.0317
Max Act: 7.3442. Min Act: -0.1700
Data Index: 2670572 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19