Model: None
Dataset: The Pile
Neuron 1878 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.1976. Min Range: -3.1976
Max Act: 3.1976. Min Act: -0.1700
Data Index: 4812295 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1976. Min Range: -3.1976
Max Act: 3.1188. Min Act: -0.1700
Data Index: 6718232 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1976. Min Range: -3.1976
Max Act: 3.0715. Min Act: -0.1700
Data Index: 4571059 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1976. Min Range: -3.1976
Max Act: 3.0242. Min Act: -0.1700
Data Index: 1188984 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1976. Min Range: -3.1976
Max Act: 3.0084. Min Act: -0.1700
Data Index: 2350784 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1976. Min Range: -3.1976
Max Act: 3.0084. Min Act: -0.1700
Data Index: 3765159 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9926. Min Act: -0.1700
Data Index: 1179335 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9926. Min Act: -0.1700
Data Index: 5132399 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9768. Min Act: -0.1700
Data Index: 681415 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9768. Min Act: -0.1700
Data Index: 347735 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9768. Min Act: -0.1700
Data Index: 2474138 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9609. Min Act: -0.1700
Data Index: 4807175 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9609. Min Act: -0.1700
Data Index: 9259045 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9609. Min Act: -0.1700
Data Index: 8167388 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9451. Min Act: -0.1700
Data Index: 5025152 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9451. Min Act: -0.1700
Data Index: 1740446 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9451. Min Act: -0.1700
Data Index: 2447482 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9293. Min Act: -0.1700
Data Index: 4612677 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9293. Min Act: -0.1700
Data Index: 3354124 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1976. Min Range: -3.1976
Max Act: 2.9293. Min Act: -0.1700
Data Index: 6365669 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19