Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2521 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1099652 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1415. Min Act: -0.0000

Data Index: 753298 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1345. Min Act: -0.0000

Data Index: 977252 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1334. Min Act: -0.0000

Data Index: 36468 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1365. Min Act: 0.0000

Data Index: 670549 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1306408 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1209. Min Act: -0.0000

Data Index: 296827 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1285. Min Act: -0.0000

Data Index: 248072 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1198. Min Act: -0.0000

Data Index: 715373 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1261581 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1143. Min Act: -0.0000

Data Index: 218032 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1147. Min Act: -0.0000

Data Index: 744230 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1152. Min Act: -0.0000

Data Index: 939914 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1344173 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1135618 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1116. Min Act: -0.0000

Data Index: 374529 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1095. Min Act: -0.0000

Data Index: 949413 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1128. Min Act: -0.0000

Data Index: 625280 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1085. Min Act: -0.0000

Data Index: 289207 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1249749 (C4 (Web Text))

Max Activating Token Index: 812