Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1759 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.5782. Min Act: -0.0001
Data Index: 1844596 (The Pile)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.5381. Min Act: -0.0001
Data Index: 1557800 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.5052. Min Act: -0.0001
Data Index: 1719383 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.5404. Min Act: -0.0001
Data Index: 1086438 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4692. Min Act: -0.0001
Data Index: 1937316 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.5109. Min Act: -0.0001
Data Index: 1051758 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4959. Min Act: -0.0001
Data Index: 1560589 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4829. Min Act: -0.0001
Data Index: 143080 (The Pile)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4679. Min Act: -0.0001
Data Index: 1073369 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4940. Min Act: -0.0001
Data Index: 207905 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4971. Min Act: -0.0001
Data Index: 667091 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.5026. Min Act: -0.0001
Data Index: 363789 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4592. Min Act: -0.0001
Data Index: 1218884 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4938. Min Act: -0.0001
Data Index: 513183 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4808. Min Act: -0.0001
Data Index: 692466 (The Pile)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4820. Min Act: -0.0001
Data Index: 758304 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4973. Min Act: -0.0001
Data Index: 879026 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4313. Min Act: -0.0001
Data Index: 523339 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4469. Min Act: -0.0001
Data Index: 99761 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5782. Min Range: -0.5782
Max Act: 0.4572. Min Act: -0.0001
Data Index: 1793651 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19