Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3479 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.9134. Min Act: -0.0001
Data Index: 508009 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.7356. Min Act: -0.0001
Data Index: 1235524 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.7248. Min Act: -0.0001
Data Index: 456372 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.7185. Min Act: -0.0001
Data Index: 1053776 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6240. Min Act: -0.0001
Data Index: 1330614 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6173. Min Act: -0.0001
Data Index: 1425463 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6722. Min Act: -0.0001
Data Index: 1845600 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6557. Min Act: -0.0001
Data Index: 134843 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6481. Min Act: -0.0001
Data Index: 1368310 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6640. Min Act: -0.0001
Data Index: 5985 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6949. Min Act: -0.0001
Data Index: 974013 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6686. Min Act: -0.0001
Data Index: 376005 (The Pile)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.5114. Min Act: -0.0001
Data Index: 302077 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6835. Min Act: -0.0001
Data Index: 1311337 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6811. Min Act: -0.0001
Data Index: 456772 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6081. Min Act: -0.0001
Data Index: 1186468 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6313. Min Act: -0.0001
Data Index: 913118 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.5951. Min Act: -0.0001
Data Index: 560421 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6685. Min Act: -0.0001
Data Index: 1797207 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9134. Min Range: -0.9134
Max Act: 0.6310. Min Act: -0.0001
Data Index: 1606407 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19