Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 747 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1457. Min Act: -0.0002

Data Index: 310109 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1245. Min Act: -0.0000

Data Index: 973822 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1263950 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1219. Min Act: -0.0003

Data Index: 368135 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1182. Min Act: -0.0003

Data Index: 477190 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1065. Min Act: -0.0001

Data Index: 696364 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1037. Min Act: -0.0003

Data Index: 168523 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1122318 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1071. Min Act: -0.0003

Data Index: 605518 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1033. Min Act: -0.0002

Data Index: 245885 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1049. Min Act: -0.0003

Data Index: 116599 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1183427 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1009. Min Act: -0.0002

Data Index: 828533 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1007. Min Act: -0.0001

Data Index: 107987 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0990. Min Act: -0.0002

Data Index: 901651 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1016. Min Act: -0.0002

Data Index: 819068 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0958. Min Act: -0.0001

Data Index: 965106 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1267178 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0986. Min Act: -0.0001

Data Index: 324953 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0984. Min Act: -0.0003

Data Index: 706935 (C4 (Web Text))

Max Activating Token Index: 889