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

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

Neuron 954 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1557. Min Act: -0.0001

Data Index: 68198 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1357. Min Act: -0.0000

Data Index: 138564 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1304455 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1150561 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1326. Min Act: -0.0000

Data Index: 319805 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1303. Min Act: -0.0001

Data Index: 959902 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1076821 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1139. Min Act: -0.0000

Data Index: 811770 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1193. Min Act: -0.0000

Data Index: 901328 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1531302 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1271067 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1611054 (Python Code)

Max Activating Token Index: 724

Text #12

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1527969 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1206. Min Act: -0.0000

Data Index: 536306 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1236018 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1124. Min Act: -0.0000

Data Index: 58080 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1562734 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1145919 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1100490 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1188216 (C4 (Web Text))

Max Activating Token Index: 884