Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.9918. Min Act: -0.1700
Data Index: 5590290 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.9292. Min Act: -0.1700
Data Index: 5091429 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.8667. Min Act: -0.1700
Data Index: 6099704 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.8667. Min Act: -0.1700
Data Index: 6995467 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.8354. Min Act: -0.1700
Data Index: 2907713 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.7729. Min Act: -0.1700
Data Index: 3106504 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.7260. Min Act: -0.1700
Data Index: 4959394 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.7260. Min Act: -0.1700
Data Index: 4637831 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.7260. Min Act: -0.1700
Data Index: 7736059 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.7416. Min Act: -0.1700
Data Index: 4734335 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.7260. Min Act: -0.1700
Data Index: 59876 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.7416. Min Act: -0.1700
Data Index: 2301956 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6790. Min Act: -0.1700
Data Index: 6979312 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6947. Min Act: -0.1700
Data Index: 59877 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6947. Min Act: -0.1700
Data Index: 6062126 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6790. Min Act: -0.1700
Data Index: 5421276 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6947. Min Act: -0.1700
Data Index: 59872 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6790. Min Act: -0.1700
Data Index: 59878 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6790. Min Act: -0.1700
Data Index: 1984917 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9918. Min Range: -3.9918
Max Act: 3.6947. Min Act: -0.1700
Data Index: 201683 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19