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

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

Neuron 2293 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: 0.1627. Min Range: -0.1627

Max Act: 0.1627. Min Act: -0.0001

Data Index: 644371 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1241209 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1368. Min Act: 0.0000

Data Index: 1231941 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1353. Min Act: -0.0001

Data Index: 724459 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1319. Min Act: -0.0000

Data Index: 951940 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1208. Min Act: -0.0001

Data Index: 597301 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1218. Min Act: -0.0001

Data Index: 592290 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1203. Min Act: -0.0001

Data Index: 447113 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1207. Min Act: -0.0001

Data Index: 234504 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1191515 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1167. Min Act: -0.0001

Data Index: 435847 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1075. Min Act: -0.0001

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1114675 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1145. Min Act: -0.0001

Data Index: 566125 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1127. Min Act: -0.0000

Data Index: 242478 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1015862 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1129. Min Act: -0.0001

Data Index: 292836 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1095. Min Act: -0.0000

Data Index: 75058 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1333045 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1049. Min Act: -0.0001

Data Index: 426319 (C4 (Web Text))

Max Activating Token Index: 956