Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3350. Min Range: -6.3350
Max Act: 6.3350. Min Act: -0.1700
Data Index: 1954556 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3350. Min Range: -6.3350
Max Act: 6.1162. Min Act: -0.1700
Data Index: 4008031 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.9912. Min Act: -0.1700
Data Index: 5600018 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.9287. Min Act: -0.1700
Data Index: 808903 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8975. Min Act: -0.1700
Data Index: 2324865 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.9287. Min Act: -0.1700
Data Index: 1463498 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8662. Min Act: -0.1700
Data Index: 21790 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8662. Min Act: -0.1700
Data Index: 5508839 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8350. Min Act: -0.1700
Data Index: 2012603 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8662. Min Act: -0.1700
Data Index: 8162475 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8350. Min Act: -0.1700
Data Index: 3747135 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.7725. Min Act: -0.1700
Data Index: 491950 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8037. Min Act: -0.1700
Data Index: 1429062 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.7412. Min Act: -0.1700
Data Index: 2726293 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.7412. Min Act: -0.1700
Data Index: 4935697 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.8037. Min Act: -0.1700
Data Index: 4326585 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.7412. Min Act: -0.1700
Data Index: 4300181 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.7725. Min Act: -0.1700
Data Index: 2215519 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.7412. Min Act: -0.1700
Data Index: 8483502 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3350. Min Range: -6.3350
Max Act: 5.7412. Min Act: -0.1700
Data Index: 4454401 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19