Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4628. Min Range: -6.4628
Max Act: 6.4628. Min Act: -0.1700
Data Index: 6666777 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4628. Min Range: -6.4628
Max Act: 6.1191. Min Act: -0.1700
Data Index: 5068106 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.9316. Min Act: -0.1700
Data Index: 1041415 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.9316. Min Act: -0.1700
Data Index: 621767 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.8691. Min Act: -0.1700
Data Index: 8058648 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.8066. Min Act: -0.1700
Data Index: 1829783 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 2287554 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.8066. Min Act: -0.1700
Data Index: 812472 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 8277862 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2877749 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 186693 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 4922517 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 7758427 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 6400766 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 7871903 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 2069603 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 4226762 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7128. Min Act: -0.1700
Data Index: 7845371 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.7128. Min Act: -0.1700
Data Index: 2667130 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4628. Min Range: -6.4628
Max Act: 5.6816. Min Act: -0.1700
Data Index: 6555573 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19