Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 30 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1223130 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0001

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0224. Min Act: -0.0000

Data Index: 186472 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1449105 (Python Code)

Max Activating Token Index: 963

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1117643 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0193. Min Act: -0.0000

Data Index: 272896 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0189. Min Act: -0.0001

Data Index: 815305 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1384580 (Python Code)

Max Activating Token Index: 226

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0179. Min Act: -0.0001

Data Index: 963697 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0188. Min Act: -0.0001

Data Index: 197520 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1656600 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0181. Min Act: -0.0001

Data Index: 421310 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0161. Min Act: -0.0001

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0170. Min Act: -0.0001

Data Index: 377051 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0169. Min Act: -0.0001

Data Index: 718272 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0178. Min Act: -0.0001

Data Index: 964184 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0172. Min Act: -0.0000

Data Index: 1370478 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1439448 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0186. Min Act: -0.0001

Data Index: 444772 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0181. Min Act: -0.0001

Data Index: 939724 (C4 (Web Text))

Max Activating Token Index: 137