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

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

Neuron 2404 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: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0001

Data Index: 310219 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1317. Min Act: -0.0001

Data Index: 178153 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1204. Min Act: -0.0001

Data Index: 551879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1251. Min Act: -0.0001

Data Index: 931545 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1229916 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1177. Min Act: -0.0001

Data Index: 81532 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1129. Min Act: -0.0001

Data Index: 350961 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1204. Min Act: -0.0001

Data Index: 697113 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1216. Min Act: -0.0001

Data Index: 324005 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1334226 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1199925 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1062. Min Act: -0.0001

Data Index: 111325 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1101. Min Act: -0.0001

Data Index: 289837 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1142. Min Act: -0.0001

Data Index: 723843 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1020545 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1327559 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1052. Min Act: -0.0001

Data Index: 906114 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1001400 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1102. Min Act: -0.0001

Data Index: 338767 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1046. Min Act: -0.0001

Data Index: 729150 (C4 (Web Text))

Max Activating Token Index: 336