Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4007 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1530. Min Act: -0.0001

Data Index: 723091 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1388. Min Act: -0.0001

Data Index: 907216 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1065603 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1080100 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1275. Min Act: -0.0001

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1279. Min Act: -0.0001

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1235. Min Act: -0.0001

Data Index: 570679 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1230609 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1209. Min Act: -0.0001

Data Index: 505491 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1199. Min Act: -0.0001

Data Index: 299446 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1158. Min Act: -0.0001

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1175. Min Act: -0.0001

Data Index: 723688 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1175. Min Act: -0.0001

Data Index: 39253 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1092801 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1174. Min Act: -0.0001

Data Index: 203847 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1129913 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1205. Min Act: -0.0001

Data Index: 152295 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1147. Min Act: -0.0001

Data Index: 180293 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1135. Min Act: -0.0000

Data Index: 447638 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1086. Min Act: -0.0001

Data Index: 588861 (C4 (Web Text))

Max Activating Token Index: 225