Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 548 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.8566. Min Act: -0.1700
Data Index: 369652 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.8566. Min Act: -0.1700
Data Index: 6532911 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.8253. Min Act: -0.1700
Data Index: 4844017 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.7003. Min Act: -0.1700
Data Index: 3835092 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.6691. Min Act: -0.1700
Data Index: 3362916 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.6378. Min Act: -0.1700
Data Index: 4773021 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.6378. Min Act: -0.1700
Data Index: 7589940 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.6066. Min Act: -0.1700
Data Index: 4265682 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.6378. Min Act: -0.1700
Data Index: 5190817 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.6066. Min Act: -0.1700
Data Index: 5327964 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.5753. Min Act: -0.1700
Data Index: 2332113 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.5441. Min Act: -0.1700
Data Index: 2550857 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.5441. Min Act: -0.1700
Data Index: 103357 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.5128. Min Act: -0.1700
Data Index: 4560928 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.5441. Min Act: -0.1700
Data Index: 6553320 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.5128. Min Act: -0.1700
Data Index: 2901992 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.5128. Min Act: -0.1700
Data Index: 6563270 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.4816. Min Act: -0.1700
Data Index: 5482464 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.4816. Min Act: -0.1700
Data Index: 1201316 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8566. Min Range: -5.8566
Max Act: 5.4816. Min Act: -0.1700
Data Index: 2435418 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19