Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.1260. Min Act: -0.1700
Data Index: 1515549 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.1260. Min Act: -0.1700
Data Index: 62264 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0589. Min Act: -0.1700
Data Index: 1658833 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0421. Min Act: -0.1700
Data Index: 1579753 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0589. Min Act: -0.1700
Data Index: 3600967 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0421. Min Act: -0.1700
Data Index: 4788737 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0253. Min Act: -0.1700
Data Index: 6035085 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0253. Min Act: -0.1699
Data Index: 4006270 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0253. Min Act: -0.1700
Data Index: 7838021 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9915. Min Act: -0.1700
Data Index: 5159042 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1260. Min Range: -2.1260
Max Act: 2.0084. Min Act: -0.1700
Data Index: 4006273 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9915. Min Act: -0.1700
Data Index: 1161984 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9915. Min Act: -0.1700
Data Index: 7195982 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9915. Min Act: -0.1700
Data Index: 8709797 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9915. Min Act: -0.1700
Data Index: 6587831 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9915. Min Act: -0.1700
Data Index: 980866 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9746. Min Act: -0.1700
Data Index: 5178798 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9746. Min Act: -0.1700
Data Index: 1265751 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9576. Min Act: -0.1700
Data Index: 6904292 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1260. Min Range: -2.1260
Max Act: 1.9915. Min Act: -0.1700
Data Index: 3919699 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19