Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1312 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0224. Min Act: -0.0001
Data Index: 890065 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0224. Min Act: -0.0001
Data Index: 390950 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0208. Min Act: -0.0001
Data Index: 1877337 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0187. Min Act: -0.0001
Data Index: 1206794 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0185. Min Act: -0.0001
Data Index: 1426126 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0185. Min Act: -0.0001
Data Index: 820998 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0182. Min Act: -0.0001
Data Index: 1047407 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0182. Min Act: -0.0001
Data Index: 1243092 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0180. Min Act: -0.0000
Data Index: 1418665 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0178. Min Act: -0.0000
Data Index: 249156 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0178. Min Act: -0.0001
Data Index: 461301 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0178. Min Act: -0.0001
Data Index: 1460548 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0177. Min Act: -0.0001
Data Index: 1639207 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0177. Min Act: -0.0001
Data Index: 513461 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0175. Min Act: -0.0001
Data Index: 803449 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0173. Min Act: -0.0001
Data Index: 1681831 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0173. Min Act: -0.0000
Data Index: 1294006 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0173. Min Act: -0.0001
Data Index: 1632054 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0165. Min Act: -0.0001
Data Index: 843510 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0224. Min Range: -0.0224
Max Act: 0.0164. Min Act: -0.0001
Data Index: 277431 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19