Model: None
Dataset: The Pile
Neuron 643 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.5093. Min Act: -0.1680
Data Index: 8417412 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4769. Min Act: -0.1700
Data Index: 5607583 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4769. Min Act: -0.1700
Data Index: 2330860 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4607. Min Act: -0.1700
Data Index: 4032473 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4444. Min Act: -0.1700
Data Index: 7370739 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4282. Min Act: -0.1699
Data Index: 8780363 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4282. Min Act: -0.1695
Data Index: 3204512 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4282. Min Act: -0.1700
Data Index: 2030249 (The Pile)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4119. Min Act: -0.1700
Data Index: 8605872 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4119. Min Act: -0.1700
Data Index: 4790793 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.4282. Min Act: -0.1700
Data Index: 7151761 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3956. Min Act: -0.1700
Data Index: 2495699 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3956. Min Act: -0.1640
Data Index: 4532410 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3956. Min Act: -0.1698
Data Index: 7766742 (The Pile)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3792. Min Act: -0.1699
Data Index: 1899329 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3956. Min Act: -0.1700
Data Index: 1209575 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3792. Min Act: -0.1700
Data Index: 2708403 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3792. Min Act: -0.1700
Data Index: 6654975 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3792. Min Act: -0.1698
Data Index: 1813626 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5093. Min Range: -2.5093
Max Act: 2.3792. Min Act: -0.1700
Data Index: 202061 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19