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

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

Neuron 1755 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0234. Min Act: -0.0002

Data Index: 606063 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1302343 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1351641 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0170. Min Act: -0.0002

Data Index: 687675 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1153523 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0166. Min Act: -0.0001

Data Index: 71489 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1478792 (Python Code)

Max Activating Token Index: 970

Text #7

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1548240 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1137498 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1074741 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0152. Min Act: -0.0001

Data Index: 800700 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0162. Min Act: -0.0001

Data Index: 948512 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0160. Min Act: -0.0001

Data Index: 625795 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0138. Min Act: -0.0002

Data Index: 347890 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1149912 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0158. Min Act: -0.0002

Data Index: 50678 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1613405 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0171. Min Act: -0.0001

Data Index: 164860 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0117. Min Act: -0.0001

Data Index: 1458649 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0162. Min Act: -0.0001

Data Index: 143072 (C4 (Web Text))

Max Activating Token Index: 113