Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0002

Data Index: 282854 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1032366 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0207. Min Act: -0.0002

Data Index: 681160 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1076178 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0198. Min Act: -0.0002

Data Index: 682399 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0189. Min Act: -0.0002

Data Index: 165660 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0181. Min Act: -0.0002

Data Index: 988513 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0180. Min Act: -0.0002

Data Index: 839556 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1024508 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0174. Min Act: -0.0002

Data Index: 14706 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0176. Min Act: -0.0002

Data Index: 880790 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0172. Min Act: -0.0002

Data Index: 726041 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0178. Min Act: -0.0002

Data Index: 719044 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1528983 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0172. Min Act: -0.0002

Data Index: 333558 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0161. Min Act: -0.0002

Data Index: 386397 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0164. Min Act: -0.0002

Data Index: 322639 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1173310 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0157. Min Act: -0.0002

Data Index: 920453 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0157. Min Act: -0.0002

Data Index: 245773 (C4 (Web Text))

Max Activating Token Index: 10