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

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

Neuron 1094 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1579. Min Act: -0.0001

Data Index: 424596 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1550. Min Act: -0.0000

Data Index: 445837 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1443. Min Act: -0.0000

Data Index: 380016 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1355. Min Act: -0.0001

Data Index: 212093 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1312746 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1222. Min Act: -0.0000

Data Index: 251727 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1292. Min Act: -0.0000

Data Index: 581283 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1290. Min Act: -0.0000

Data Index: 199195 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1229212 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1111919 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1216308 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1259902 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1155. Min Act: -0.0001

Data Index: 729206 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1118. Min Act: -0.0000

Data Index: 545420 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1125. Min Act: -0.0000

Data Index: 684986 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1132. Min Act: -0.0000

Data Index: 924432 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1150. Min Act: -0.0000

Data Index: 85622 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1132. Min Act: 0.0000

Data Index: 1313057 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1150054 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1294548 (C4 (Web Text))

Max Activating Token Index: 835