Model: None
Dataset: The Pile
Neuron 3971 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.4559. Min Act: -0.1700
Data Index: 1188401 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3775. Min Act: -0.1700
Data Index: 2092925 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3618. Min Act: -0.1700
Data Index: 2726605 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3461. Min Act: -0.1700
Data Index: 5078479 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3304. Min Act: -0.1700
Data Index: 4617340 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3304. Min Act: -0.1700
Data Index: 8091881 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3147. Min Act: -0.1700
Data Index: 8496056 (The Pile)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3147. Min Act: -0.1700
Data Index: 9035577 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3147. Min Act: -0.1700
Data Index: 1549047 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3147. Min Act: -0.1700
Data Index: 8228338 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.3147. Min Act: -0.1700
Data Index: 2182345 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2990. Min Act: -0.1700
Data Index: 10496549 (The Pile)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2990. Min Act: -0.1700
Data Index: 10556340 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2990. Min Act: -0.1700
Data Index: 9985301 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2990. Min Act: -0.1700
Data Index: 10584250 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2833. Min Act: -0.1700
Data Index: 7268274 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2833. Min Act: -0.1700
Data Index: 658501 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2833. Min Act: -0.1700
Data Index: 10448060 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2833. Min Act: -0.1700
Data Index: 6736526 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4559. Min Range: -3.4559
Max Act: 3.2833. Min Act: -0.1700
Data Index: 3674597 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19