Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 948 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0005

Data Index: 966869 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1447. Min Act: -0.0005

Data Index: 162221 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1334. Min Act: -0.0005

Data Index: 367733 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1256. Min Act: -0.0005

Data Index: 1159265 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1247. Min Act: -0.0005

Data Index: 1094987 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1232. Min Act: -0.0005

Data Index: 364547 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1239. Min Act: -0.0005

Data Index: 1130769 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1217. Min Act: -0.0005

Data Index: 921652 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1247. Min Act: -0.0005

Data Index: 23236 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1183. Min Act: -0.0005

Data Index: 24778 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1177. Min Act: -0.0005

Data Index: 1194940 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1173. Min Act: -0.0005

Data Index: 1062795 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1173. Min Act: -0.0005

Data Index: 496365 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1203. Min Act: -0.0005

Data Index: 716745 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1166. Min Act: -0.0005

Data Index: 568390 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1151. Min Act: -0.0005

Data Index: 381880 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1055. Min Act: -0.0005

Data Index: 1121008 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1094. Min Act: -0.0005

Data Index: 255281 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1043. Min Act: -0.0005

Data Index: 1299927 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1046. Min Act: -0.0005

Data Index: 1059878 (C4 (Web Text))

Max Activating Token Index: 68