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

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

Neuron 2954 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0204. Min Act: -0.0003

Data Index: 77907 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0003

Data Index: 719449 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0191. Min Act: -0.0003

Data Index: 126240 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0186. Min Act: -0.0003

Data Index: 780841 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0213. Min Act: -0.0003

Data Index: 627041 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1278987 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1060731 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1476090 (Python Code)

Max Activating Token Index: 772

Text #8

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0175. Min Act: -0.0003

Data Index: 26632 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1549327 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0172. Min Act: -0.0003

Data Index: 937782 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1446047 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0155. Min Act: -0.0003

Data Index: 118745 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0173. Min Act: -0.0003

Data Index: 207146 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0156. Min Act: -0.0003

Data Index: 799285 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1624392 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0164. Min Act: -0.0003

Data Index: 220226 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1564344 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0174. Min Act: -0.0003

Data Index: 832387 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1093172 (C4 (Web Text))

Max Activating Token Index: 227