Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 722 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0005

Data Index: 327713 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0316. Min Act: -0.0005

Data Index: 892319 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0293. Min Act: -0.0005

Data Index: 233924 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0306. Min Act: -0.0005

Data Index: 911598 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0290. Min Act: -0.0005

Data Index: 980386 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1143622 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0285. Min Act: -0.0005

Data Index: 765039 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1107836 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1288683 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1270233 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0270. Min Act: -0.0005

Data Index: 420159 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0264. Min Act: -0.0005

Data Index: 1209581 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1067055 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0255. Min Act: -0.0005

Data Index: 639090 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0253. Min Act: -0.0005

Data Index: 432350 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0257. Min Act: -0.0005

Data Index: 408604 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0253. Min Act: -0.0005

Data Index: 1095986 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0249. Min Act: -0.0005

Data Index: 235506 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0251. Min Act: -0.0005

Data Index: 1016137 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0255. Min Act: -0.0005

Data Index: 23281 (C4 (Web Text))

Max Activating Token Index: 303