Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0769. Min Range: -9.0769
Max Act: 8.5769. Min Act: -0.1700
Data Index: 4187037 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0769. Min Range: -9.0769
Max Act: 9.0769. Min Act: -0.1700
Data Index: 1203490 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0769. Min Range: -9.0769
Max Act: 8.2957. Min Act: -0.1700
Data Index: 6008875 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0769. Min Range: -9.0769
Max Act: 8.2957. Min Act: -0.1700
Data Index: 2485550 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0769. Min Range: -9.0769
Max Act: 8.0457. Min Act: -0.1700
Data Index: 8340305 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0769. Min Range: -9.0769
Max Act: 8.1394. Min Act: -0.1700
Data Index: 6707119 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.1394. Min Act: -0.1700
Data Index: 2226042 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.8269. Min Act: -0.1700
Data Index: 8034533 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.5457. Min Act: -0.1700
Data Index: 340280 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0769. Min Range: -9.0769
Max Act: 6.4832. Min Act: -0.1700
Data Index: 124697 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.9519. Min Act: -0.1700
Data Index: 3065858 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.9832. Min Act: -0.1700
Data Index: 1235769 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.8582. Min Act: -0.1700
Data Index: 2865030 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.8582. Min Act: -0.1700
Data Index: 7670353 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.6394. Min Act: -0.1700
Data Index: 4039727 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.9519. Min Act: -0.1700
Data Index: 4548083 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.8582. Min Act: -0.1700
Data Index: 6172845 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.7332. Min Act: -0.1700
Data Index: 4658098 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.8582. Min Act: -0.1700
Data Index: 212437 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0769. Min Range: -9.0769
Max Act: 7.2019. Min Act: -0.1700
Data Index: 5648360 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19