Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1051 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0266. Min Act: -0.0001
Data Index: 1102052 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0240. Min Act: -0.0001
Data Index: 562635 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0209. Min Act: -0.0001
Data Index: 432613 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0192. Min Act: -0.0001
Data Index: 646958 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0176. Min Act: -0.0001
Data Index: 1063991 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0181. Min Act: -0.0001
Data Index: 587199 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0171. Min Act: -0.0001
Data Index: 186216 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0166. Min Act: -0.0001
Data Index: 590449 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0175. Min Act: -0.0001
Data Index: 536747 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0161. Min Act: -0.0001
Data Index: 784703 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0158. Min Act: -0.0001
Data Index: 467914 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0163. Min Act: -0.0001
Data Index: 791607 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0149. Min Act: -0.0001
Data Index: 1432408 (Python Code)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0137. Min Act: -0.0001
Data Index: 540696 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0158. Min Act: -0.0001
Data Index: 1504513 (Python Code)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0149. Min Act: -0.0001
Data Index: 207456 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0140. Min Act: -0.0001
Data Index: 1126801 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0137. Min Act: -0.0001
Data Index: 523565 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0135. Min Act: -0.0001
Data Index: 1281427 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0266. Min Range: -0.0266
Max Act: 0.0151. Min Act: -0.0001
Data Index: 1034950 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19