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

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

Neuron 3973 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.5245. Min Act: -0.0000

Data Index: 19255 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.3825. Min Act: -0.0000

Data Index: 986681 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.3564. Min Act: -0.0001

Data Index: 897564 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1350844 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.1610. Min Act: -0.0000

Data Index: 84793 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.1262. Min Act: -0.0000

Data Index: 111496 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1249616 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.1132. Min Act: -0.0001

Data Index: 29209 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.1039. Min Act: -0.0001

Data Index: 998010 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 1.5245. Min Range: -1.5245

Max Act: 0.9401. Min Act: -0.0000

Data Index: 384857 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.0454. Min Act: -0.0000

Data Index: 808284 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1112425 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 1.5245. Min Range: -1.5245

Max Act: 0.9024. Min Act: -0.0001

Data Index: 617618 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.0311. Min Act: -0.0000

Data Index: 331278 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 1.5245. Min Range: -1.5245

Max Act: 0.9553. Min Act: -0.0001

Data Index: 1203262 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.5245. Min Range: -1.5245

Max Act: 1.0060. Min Act: -0.0001

Data Index: 485955 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.5245. Min Range: -1.5245

Max Act: 0.9446. Min Act: -0.0000

Data Index: 229309 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.5245. Min Range: -1.5245

Max Act: 0.9580. Min Act: -0.0001

Data Index: 220761 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.5245. Min Range: -1.5245

Max Act: 0.9224. Min Act: -0.0000

Data Index: 815330 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.5245. Min Range: -1.5245

Max Act: 0.9257. Min Act: -0.0000

Data Index: 866511 (C4 (Web Text))

Max Activating Token Index: 336