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

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

Neuron 1936 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1323428 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: -0.0001

Data Index: 570227 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1362. Min Act: -0.0001

Data Index: 203300 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1319. Min Act: -0.0001

Data Index: 445364 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1323. Min Act: -0.0001

Data Index: 255726 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1380. Min Act: -0.0001

Data Index: 517732 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1039400 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1221. Min Act: -0.0001

Data Index: 837786 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1549571 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1251. Min Act: -0.0001

Data Index: 273158 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1285. Min Act: -0.0001

Data Index: 67329 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1584801 (Python Code)

Max Activating Token Index: 111

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1570600 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1211. Min Act: -0.0001

Data Index: 64808 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1089241 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1147. Min Act: -0.0001

Data Index: 428587 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1175. Min Act: -0.0001

Data Index: 111105 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1467493 (Python Code)

Max Activating Token Index: 266

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1165129 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1138. Min Act: -0.0001

Data Index: 453160 (C4 (Web Text))

Max Activating Token Index: 601