Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 665 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1699. Min Act: -0.0000

Data Index: 342081 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1514. Min Act: -0.0000

Data Index: 916466 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1352. Min Act: -0.0001

Data Index: 422194 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1334. Min Act: -0.0001

Data Index: 544815 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1325. Min Act: -0.0001

Data Index: 874344 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1347. Min Act: 0.0000

Data Index: 1194650 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1305. Min Act: -0.0001

Data Index: 995683 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1265. Min Act: -0.0001

Data Index: 468623 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1272. Min Act: -0.0001

Data Index: 109164 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1005821 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1306927 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1236. Min Act: -0.0001

Data Index: 893580 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1223. Min Act: -0.0000

Data Index: 384329 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1201. Min Act: -0.0001

Data Index: 377325 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1159. Min Act: -0.0001

Data Index: 838827 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1353. Min Act: 0.0000

Data Index: 990390 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1080591 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1354987 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1138. Min Act: 0.0001

Data Index: 1065363 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1175. Min Act: -0.0000

Data Index: 396660 (C4 (Web Text))

Max Activating Token Index: 444