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

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

Neuron 3901 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: 0.1532. Min Range: -0.1532

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1236226 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1379. Min Act: -0.0001

Data Index: 745564 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1418. Min Act: -0.0001

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1381. Min Act: -0.0001

Data Index: 868138 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1134815 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1309. Min Act: -0.0001

Data Index: 362162 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1294. Min Act: -0.0001

Data Index: 336458 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1132. Min Act: -0.0001

Data Index: 12069 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1207745 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1031492 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1366. Min Act: -0.0001

Data Index: 691618 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1199. Min Act: -0.0001

Data Index: 2308 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1046. Min Act: -0.0001

Data Index: 13905 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1160. Min Act: -0.0001

Data Index: 870444 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1091. Min Act: -0.0001

Data Index: 628004 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1086. Min Act: -0.0001

Data Index: 155436 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0965. Min Act: -0.0002

Data Index: 196675 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1005. Min Act: -0.0001

Data Index: 231572 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1114. Min Act: -0.0001

Data Index: 19089 (C4 (Web Text))

Max Activating Token Index: 136