Model: None
Dataset: The Pile
Neuron 1019 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.9465. Min Act: -0.1700
Data Index: 1048553 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.9148. Min Act: -0.1700
Data Index: 6952645 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.9148. Min Act: -0.1700
Data Index: 4644889 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.9148. Min Act: -0.1700
Data Index: 2682655 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.9148. Min Act: -0.1700
Data Index: 10145006 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.9148. Min Act: -0.1700
Data Index: 9188564 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.9148. Min Act: -0.1700
Data Index: 3316862 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.8990. Min Act: -0.1700
Data Index: 5409675 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.8513. Min Act: -0.1700
Data Index: 6301240 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.8354. Min Act: -0.1700
Data Index: 4281045 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.8195. Min Act: -0.1700
Data Index: 1029014 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.8195. Min Act: -0.1700
Data Index: 4229914 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7877. Min Act: -0.1700
Data Index: 6087768 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7877. Min Act: -0.1700
Data Index: 2884351 (The Pile)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7717. Min Act: -0.1700
Data Index: 6069730 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7717. Min Act: -0.1699
Data Index: 4032421 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7558. Min Act: -0.1700
Data Index: 2062865 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7558. Min Act: -0.1700
Data Index: 1663628 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7398. Min Act: -0.1700
Data Index: 3353268 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9465. Min Range: -2.9465
Max Act: 2.7398. Min Act: -0.1700
Data Index: 8730138 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19