Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0003

Data Index: 630488 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1318. Min Act: -0.0003

Data Index: 206808 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1378. Min Act: -0.0004

Data Index: 1088528 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1286. Min Act: -0.0003

Data Index: 532447 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1221. Min Act: -0.0003

Data Index: 1248052 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1218. Min Act: -0.0003

Data Index: 155166 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1187. Min Act: -0.0003

Data Index: 1206443 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1214. Min Act: -0.0003

Data Index: 144275 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1143. Min Act: -0.0003

Data Index: 357678 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1183. Min Act: -0.0003

Data Index: 603951 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1177. Min Act: -0.0003

Data Index: 1151911 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1166. Min Act: -0.0003

Data Index: 8715 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1120. Min Act: -0.0003

Data Index: 416887 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1143. Min Act: -0.0003

Data Index: 306158 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1114. Min Act: -0.0003

Data Index: 301862 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1073. Min Act: -0.0003

Data Index: 186168 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1128. Min Act: -0.0003

Data Index: 720246 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1092. Min Act: -0.0003

Data Index: 442153 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1112. Min Act: -0.0003

Data Index: 386218 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1092. Min Act: -0.0003

Data Index: 414160 (C4 (Web Text))

Max Activating Token Index: 858