Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.8311. Min Act: -0.1700
Data Index: 8480889 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.8623. Min Act: -0.1700
Data Index: 2765480 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.8311. Min Act: -0.1700
Data Index: 2954947 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.7998. Min Act: -0.1700
Data Index: 8272514 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.6748. Min Act: -0.1700
Data Index: 2024251 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.6748. Min Act: -0.1700
Data Index: 716757 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.7061. Min Act: -0.1700
Data Index: 102402 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.6748. Min Act: -0.1700
Data Index: 7470903 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.6436. Min Act: -0.1700
Data Index: 3474983 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.6123. Min Act: -0.1700
Data Index: 1366300 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5811. Min Act: -0.1700
Data Index: 7928351 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5811. Min Act: -0.1700
Data Index: 7095522 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5811. Min Act: -0.1700
Data Index: 1944483 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5811. Min Act: -0.1700
Data Index: 2776753 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5186. Min Act: -0.1700
Data Index: 81562 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5498. Min Act: -0.1700
Data Index: 6309768 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5186. Min Act: -0.1700
Data Index: 6699788 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5186. Min Act: -0.1699
Data Index: 2506766 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.4873. Min Act: -0.1700
Data Index: 6573620 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8623. Min Range: -7.8623
Max Act: 7.5186. Min Act: -0.1700
Data Index: 2189847 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19