Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.9232. Min Act: -0.1700
Data Index: 333535 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.8607. Min Act: -0.1700
Data Index: 6261767 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.7982. Min Act: -0.1700
Data Index: 4895930 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.7982. Min Act: -0.1700
Data Index: 1108961 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.7357. Min Act: -0.1700
Data Index: 7980679 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.5482. Min Act: -0.1700
Data Index: 1264030 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.3607. Min Act: -0.1700
Data Index: 3055143 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.4232. Min Act: -0.1700
Data Index: 4438960 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.3607. Min Act: -0.1700
Data Index: 3789748 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.3607. Min Act: -0.1700
Data Index: 8190523 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.3607. Min Act: -0.1700
Data Index: 6661772 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2982. Min Act: -0.1700
Data Index: 6936296 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2982. Min Act: -0.1700
Data Index: 7832185 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2982. Min Act: -0.1700
Data Index: 2511448 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2982. Min Act: -0.1700
Data Index: 5425155 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2982. Min Act: -0.1700
Data Index: 7109808 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.1732. Min Act: -0.1700
Data Index: 4311329 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2357. Min Act: -0.1700
Data Index: 1341940 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.1732. Min Act: -0.1700
Data Index: 443482 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2982. Min Act: -0.1700
Data Index: 2376290 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19