Model: None
Dataset: The Pile
Neuron 3550 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.4213. Min Act: -0.1700
Data Index: 4931966 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3899. Min Act: -0.1700
Data Index: 1500030 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2958. Min Act: -0.1700
Data Index: 3031617 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2958. Min Act: -0.1700
Data Index: 8595703 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2801. Min Act: -0.1700
Data Index: 5583906 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1857. Min Act: -0.1700
Data Index: 3238532 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1385. Min Act: -0.1700
Data Index: 947271 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1227. Min Act: -0.1700
Data Index: 5598852 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1070. Min Act: -0.1700
Data Index: 5577367 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1070. Min Act: -0.1700
Data Index: 1583196 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0912. Min Act: -0.1700
Data Index: 195020 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0912. Min Act: -0.1700
Data Index: 2933270 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0912. Min Act: -0.1700
Data Index: 9097468 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0912. Min Act: -0.1700
Data Index: 8793229 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0912. Min Act: -0.1700
Data Index: 660036 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0754. Min Act: -0.1700
Data Index: 8598135 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0754. Min Act: -0.1700
Data Index: 9769673 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0754. Min Act: -0.1700
Data Index: 10049713 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0596. Min Act: -0.1700
Data Index: 7147643 (The Pile)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0596. Min Act: -0.1700
Data Index: 8631383 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19