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

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

Neuron 3057 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1443859 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1654299 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1499304 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1518547 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1641619 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1517215 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1629387 (Python Code)

Max Activating Token Index: 940

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1512535 (Python Code)

Max Activating Token Index: 176

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1471077 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1612031 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1383792 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1652939 (Python Code)

Max Activating Token Index: 655

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1361509 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1445718 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1475714 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1408424 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1460423 (Python Code)

Max Activating Token Index: 444

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1461875 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1418400 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1649389 (Python Code)

Max Activating Token Index: 686