Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3204 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0954. Min Act: -0.0003
Data Index: 594919 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0849. Min Act: -0.0003
Data Index: 965049 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0770. Min Act: -0.0003
Data Index: 1165763 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0768. Min Act: -0.0003
Data Index: 1415855 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0778. Min Act: -0.0003
Data Index: 1879884 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0748. Min Act: -0.0003
Data Index: 1671554 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0714. Min Act: -0.0003
Data Index: 1003493 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0722. Min Act: -0.0003
Data Index: 970434 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0683. Min Act: -0.0003
Data Index: 1561025 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0710. Min Act: -0.0003
Data Index: 1436030 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0750. Min Act: -0.0003
Data Index: 1200737 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0651. Min Act: -0.0003
Data Index: 286087 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0683. Min Act: -0.0003
Data Index: 602516 (The Pile)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0703. Min Act: -0.0003
Data Index: 655319 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0673. Min Act: -0.0003
Data Index: 236322 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0653. Min Act: -0.0003
Data Index: 383246 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0674. Min Act: -0.0003
Data Index: 1105731 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0611. Min Act: -0.0003
Data Index: 767660 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0669. Min Act: -0.0003
Data Index: 495121 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0954. Min Range: -0.0954
Max Act: 0.0632. Min Act: -0.0003
Data Index: 1237491 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19