Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3718 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0301. Min Act: -0.0001
Data Index: 1021301 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0260. Min Act: -0.0001
Data Index: 434107 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0245. Min Act: -0.0001
Data Index: 1084301 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0242. Min Act: -0.0001
Data Index: 564212 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0219. Min Act: -0.0001
Data Index: 191966 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0223. Min Act: -0.0001
Data Index: 890753 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0206. Min Act: -0.0001
Data Index: 1648538 (Python Code)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0197. Min Act: -0.0001
Data Index: 1101004 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0182. Min Act: -0.0001
Data Index: 1073920 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0181. Min Act: -0.0001
Data Index: 163380 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0165. Min Act: -0.0001
Data Index: 355025 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0159. Min Act: -0.0001
Data Index: 110736 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0137. Min Act: -0.0001
Data Index: 251151 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0142. Min Act: -0.0001
Data Index: 785892 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0159. Min Act: -0.0001
Data Index: 1171269 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0148. Min Act: -0.0001
Data Index: 446048 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0159. Min Act: -0.0001
Data Index: 111116 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0153. Min Act: -0.0001
Data Index: 1638395 (Python Code)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0151. Min Act: -0.0001
Data Index: 1429493 (Python Code)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0301. Min Range: -0.0301
Max Act: 0.0149. Min Act: -0.0001
Data Index: 1303136 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19