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

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

Neuron 224 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0221. Min Act: -0.0006

Data Index: 881145 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0006

Data Index: 92960 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0191. Min Act: -0.0006

Data Index: 870516 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0208. Min Act: -0.0006

Data Index: 216960 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0211. Min Act: -0.0006

Data Index: 572621 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0203. Min Act: -0.0006

Data Index: 977067 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0199. Min Act: -0.0006

Data Index: 73162 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1080924 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0194. Min Act: -0.0006

Data Index: 967990 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0186. Min Act: -0.0006

Data Index: 175604 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0006

Data Index: 980228 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0197. Min Act: -0.0006

Data Index: 25158 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0196. Min Act: -0.0006

Data Index: 331559 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1220445 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0184. Min Act: -0.0006

Data Index: 472608 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0197. Min Act: -0.0006

Data Index: 653215 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1009364 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0166. Min Act: -0.0006

Data Index: 243208 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0191. Min Act: -0.0006

Data Index: 930959 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0199. Min Act: -0.0006

Data Index: 10064 (C4 (Web Text))

Max Activating Token Index: 365