Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5664 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.5362. Min Act: -0.1700
Data Index: 1455515 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.3487. Min Act: -0.1700
Data Index: 435925 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.2862. Min Act: -0.1700
Data Index: 7393835 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.2862. Min Act: -0.1700
Data Index: 1027125 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.1612. Min Act: -0.1700
Data Index: 8611623 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.1612. Min Act: -0.1700
Data Index: 8127567 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.1612. Min Act: -0.1700
Data Index: 52951 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.0987. Min Act: -0.1700
Data Index: 5104987 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.0987. Min Act: -0.1700
Data Index: 3275508 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.0987. Min Act: -0.1700
Data Index: 8116852 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.0362. Min Act: -0.1700
Data Index: 1606913 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.0362. Min Act: -0.1700
Data Index: 2037000 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.0362. Min Act: -0.1700
Data Index: 8495832 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5362. Min Range: -8.5362
Max Act: 8.0362. Min Act: -0.1700
Data Index: 339495 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5362. Min Range: -8.5362
Max Act: 7.9737. Min Act: -0.1700
Data Index: 7236256 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5362. Min Range: -8.5362
Max Act: 7.9737. Min Act: -0.1700
Data Index: 964371 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5362. Min Range: -8.5362
Max Act: 7.9737. Min Act: -0.1700
Data Index: 4132464 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5362. Min Range: -8.5362
Max Act: 7.9737. Min Act: -0.1700
Data Index: 870092 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5362. Min Range: -8.5362
Max Act: 7.9112. Min Act: -0.1700
Data Index: 2766985 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5362. Min Range: -8.5362
Max Act: 7.8487. Min Act: -0.1700
Data Index: 727639 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19