Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1546. Min Act: -0.0001

Data Index: 836767 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1312048 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1466. Min Act: -0.0001

Data Index: 312492 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1303. Min Act: -0.0001

Data Index: 167818 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1302. Min Act: -0.0001

Data Index: 990006 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1299. Min Act: -0.0001

Data Index: 949972 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1234. Min Act: -0.0001

Data Index: 873222 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1199. Min Act: -0.0001

Data Index: 388211 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1100650 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1233. Min Act: -0.0001

Data Index: 105591 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1196. Min Act: -0.0001

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1223. Min Act: -0.0001

Data Index: 907987 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1254859 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1176. Min Act: -0.0001

Data Index: 984183 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1190307 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1334342 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1193. Min Act: -0.0001

Data Index: 201959 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1137. Min Act: -0.0001

Data Index: 609585 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1160. Min Act: -0.0001

Data Index: 370350 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1218. Min Act: -0.0001

Data Index: 523930 (C4 (Web Text))

Max Activating Token Index: 302