Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 155 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0001

Data Index: 332921 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1381. Min Act: -0.0001

Data Index: 612251 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1335. Min Act: -0.0001

Data Index: 609711 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1303. Min Act: -0.0000

Data Index: 852282 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1344. Min Act: -0.0001

Data Index: 514675 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1387. Min Act: -0.0001

Data Index: 998142 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1243902 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1248. Min Act: -0.0000

Data Index: 592223 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1294. Min Act: -0.0000

Data Index: 681205 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1291. Min Act: -0.0001

Data Index: 570197 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1243. Min Act: -0.0001

Data Index: 160069 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1159. Min Act: -0.0001

Data Index: 774348 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1166. Min Act: -0.0000

Data Index: 779311 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1043. Min Act: -0.0000

Data Index: 201231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1318839 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1051943 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1281754 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1401523 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1270. Min Act: -0.0001

Data Index: 59124 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1211. Min Act: -0.0000

Data Index: 94886 (C4 (Web Text))

Max Activating Token Index: 925