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

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

Neuron 2930 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1123840 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1356445 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1405. Min Act: -0.0001

Data Index: 990688 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1054140 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1411. Min Act: -0.0001

Data Index: 593007 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1441. Min Act: -0.0001

Data Index: 28397 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1514. Min Act: -0.0001

Data Index: 287564 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1258. Min Act: -0.0001

Data Index: 698901 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1235192 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1352. Min Act: -0.0001

Data Index: 453734 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1195. Min Act: -0.0001

Data Index: 749974 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1451140 (Python Code)

Max Activating Token Index: 918

Text #13

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1087. Min Act: -0.0001

Data Index: 334957 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1078. Min Act: -0.0001

Data Index: 407838 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1170. Min Act: -0.0001

Data Index: 420119 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1164. Min Act: -0.0001

Data Index: 917211 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1139. Min Act: -0.0001

Data Index: 651990 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1169. Min Act: -0.0001

Data Index: 369229 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1226588 (C4 (Web Text))

Max Activating Token Index: 434