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

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

Neuron 145 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: 0.1417. Min Range: -0.1417

Max Act: 0.1345. Min Act: -0.0001

Data Index: 864460 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1370. Min Act: -0.0001

Data Index: 869560 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1417. Min Act: -0.0001

Data Index: 610484 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1209. Min Act: -0.0001

Data Index: 171352 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1268252 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1057699 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1339803 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1010247 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1164. Min Act: -0.0001

Data Index: 904309 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1209. Min Act: -0.0001

Data Index: 858557 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1257. Min Act: -0.0001

Data Index: 567186 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1153. Min Act: -0.0001

Data Index: 468630 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1294959 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1178. Min Act: -0.0001

Data Index: 740798 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1215. Min Act: -0.0001

Data Index: 259728 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1259. Min Act: -0.0001

Data Index: 840550 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1170. Min Act: -0.0001

Data Index: 807971 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1157. Min Act: -0.0001

Data Index: 843474 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1068509 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1198. Min Act: -0.0001

Data Index: 628015 (C4 (Web Text))

Max Activating Token Index: 1012