Model: None
Dataset: The Pile
Neuron 3901 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.6149. Min Act: -0.1700
Data Index: 4042415 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5836. Min Act: -0.1699
Data Index: 6614863 (The Pile)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5209. Min Act: -0.1700
Data Index: 8631595 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5209. Min Act: -0.1700
Data Index: 8480154 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5052. Min Act: -0.1700
Data Index: 5535584 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5052. Min Act: -0.1700
Data Index: 9224157 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4896. Min Act: -0.1700
Data Index: 1502092 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4739. Min Act: -0.1700
Data Index: 8683284 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4582. Min Act: -0.1700
Data Index: 7762171 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4582. Min Act: -0.1700
Data Index: 4309925 (The Pile)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4582. Min Act: -0.1700
Data Index: 5759264 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4426. Min Act: -0.1700
Data Index: 5944060 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4426. Min Act: -0.1700
Data Index: 1209135 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4426. Min Act: -0.1700
Data Index: 8572532 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4426. Min Act: -0.1700
Data Index: 3490903 (The Pile)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4426. Min Act: -0.1700
Data Index: 3855057 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4426. Min Act: -0.1700
Data Index: 8729942 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4269. Min Act: -0.1700
Data Index: 2089404 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4269. Min Act: -0.1700
Data Index: 1611485 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4269. Min Act: -0.1700
Data Index: 6128707 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19