Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.4843. Min Act: -0.1700
Data Index: 2152153 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.4530. Min Act: -0.1700
Data Index: 574538 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.4843. Min Act: -0.1700
Data Index: 6058749 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.3905. Min Act: -0.1700
Data Index: 3264284 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2655. Min Act: -0.1700
Data Index: 4309402 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2655. Min Act: -0.1700
Data Index: 7627731 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2343. Min Act: -0.1700
Data Index: 3887664 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2343. Min Act: -0.1700
Data Index: 2158003 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2030. Min Act: -0.1700
Data Index: 8439473 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2343. Min Act: -0.1700
Data Index: 7581400 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2030. Min Act: -0.1700
Data Index: 343841 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.2030. Min Act: -0.1700
Data Index: 2449478 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.1718. Min Act: -0.1700
Data Index: 7643255 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.0780. Min Act: -0.1700
Data Index: 3283576 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.1093. Min Act: -0.1700
Data Index: 2424693 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.1093. Min Act: -0.1700
Data Index: 3917991 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.0780. Min Act: -0.1700
Data Index: 7534302 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.0780. Min Act: -0.1700
Data Index: 8150910 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.0468. Min Act: -0.1700
Data Index: 215302 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4843. Min Range: -6.4843
Max Act: 6.0468. Min Act: -0.1700
Data Index: 5213225 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19