Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2022 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1121955 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1224. Min Act: -0.0001

Data Index: 93598 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1318. Min Act: -0.0001

Data Index: 617489 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1321318 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1009. Min Act: -0.0001

Data Index: 597942 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1126925 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1158. Min Act: -0.0001

Data Index: 672259 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1021. Min Act: -0.0001

Data Index: 622860 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1044. Min Act: -0.0001

Data Index: 61390 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1045656 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0998. Min Act: -0.0001

Data Index: 578355 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1006. Min Act: -0.0001

Data Index: 345801 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1296366 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1153464 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1268310 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0973. Min Act: -0.0001

Data Index: 563695 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0950. Min Act: -0.0002

Data Index: 860188 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0993. Min Act: -0.0001

Data Index: 107933 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1000. Min Act: -0.0001

Data Index: 877317 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1013236 (C4 (Web Text))

Max Activating Token Index: 554