Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2832 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.9022. Min Act: -0.0003
Data Index: 1850328 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.8787. Min Act: -0.0003
Data Index: 1630650 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.8018. Min Act: -0.0003
Data Index: 1552860 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.8277. Min Act: -0.0003
Data Index: 687187 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7934. Min Act: -0.0003
Data Index: 175713 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7723. Min Act: -0.0003
Data Index: 1899889 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.8194. Min Act: -0.0003
Data Index: 1514965 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7864. Min Act: -0.0003
Data Index: 1798356 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7811. Min Act: -0.0003
Data Index: 284742 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7653. Min Act: -0.0003
Data Index: 1902809 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7630. Min Act: -0.0003
Data Index: 591721 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7530. Min Act: -0.0003
Data Index: 1704225 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7748. Min Act: -0.0003
Data Index: 1793207 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7715. Min Act: -0.0003
Data Index: 1300884 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7221. Min Act: -0.0003
Data Index: 1699056 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7375. Min Act: -0.0003
Data Index: 268321 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7608. Min Act: -0.0003
Data Index: 75343 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7403. Min Act: -0.0003
Data Index: 35384 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7354. Min Act: -0.0003
Data Index: 1924796 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9022. Min Range: -0.9022
Max Act: 0.7371. Min Act: -0.0003
Data Index: 981856 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19