Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0177. Min Act: -0.0002

Data Index: 782116 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0168. Min Act: -0.0002

Data Index: 618956 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1193284 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1191484 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0165. Min Act: -0.0002

Data Index: 491163 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0141. Min Act: -0.0002

Data Index: 529934 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0171. Min Act: -0.0002

Data Index: 347270 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0155. Min Act: -0.0002

Data Index: 29449 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0150. Min Act: -0.0002

Data Index: 522517 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0157. Min Act: -0.0002

Data Index: 795436 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0155. Min Act: -0.0002

Data Index: 370033 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1274285 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0148. Min Act: -0.0002

Data Index: 321280 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1344299 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0150. Min Act: -0.0002

Data Index: 419035 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0141. Min Act: -0.0002

Data Index: 454434 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1228425 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0156. Min Act: -0.0002

Data Index: 779991 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1014171 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0124. Min Act: -0.0002

Data Index: 371822 (C4 (Web Text))

Max Activating Token Index: 582