Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3294 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0196. Min Act: -0.0001
Data Index: 1959719 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0191. Min Act: -0.0001
Data Index: 274267 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0190. Min Act: -0.0001
Data Index: 757822 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0186. Min Act: -0.0001
Data Index: 1775308 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0186. Min Act: -0.0001
Data Index: 1059765 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0186. Min Act: -0.0001
Data Index: 1265164 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0185. Min Act: -0.0001
Data Index: 803867 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0184. Min Act: -0.0001
Data Index: 1392736 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0186. Min Act: -0.0001
Data Index: 622543 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0183. Min Act: -0.0001
Data Index: 288324 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0184. Min Act: -0.0001
Data Index: 295554 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0180. Min Act: -0.0001
Data Index: 311180 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0180. Min Act: -0.0001
Data Index: 1708986 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0180. Min Act: -0.0001
Data Index: 702725 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0180. Min Act: -0.0001
Data Index: 402713 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0180. Min Act: -0.0001
Data Index: 576705 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0176. Min Act: -0.0001
Data Index: 926676 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0175. Min Act: -0.0001
Data Index: 1957881 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0176. Min Act: -0.0001
Data Index: 1280034 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0196. Min Range: -0.0196
Max Act: 0.0175. Min Act: -0.0001
Data Index: 173967 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19