Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1190 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0001

Data Index: 300774 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1117. Min Act: -0.0001

Data Index: 187071 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1230. Min Act: -0.0001

Data Index: 171388 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1164. Min Act: -0.0001

Data Index: 549677 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1279. Min Act: -0.0001

Data Index: 163966 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1247656 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1182. Min Act: -0.0001

Data Index: 217859 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1041. Min Act: -0.0001

Data Index: 849327 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1170. Min Act: -0.0001

Data Index: 857086 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1226683 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1188. Min Act: -0.0001

Data Index: 127634 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1280063 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1184125 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1120. Min Act: -0.0001

Data Index: 975443 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0976. Min Act: -0.0001

Data Index: 771215 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1034. Min Act: -0.0001

Data Index: 118609 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0995. Min Act: -0.0001

Data Index: 15817 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1067. Min Act: -0.0001

Data Index: 878501 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1088. Min Act: -0.0001

Data Index: 87404 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1083224 (C4 (Web Text))

Max Activating Token Index: 610