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

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

Neuron 1589 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1523. Min Act: -0.0002

Data Index: 588886 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1063394 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1404. Min Act: -0.0002

Data Index: 621383 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1391. Min Act: -0.0002

Data Index: 1018653 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1474. Min Act: -0.0002

Data Index: 742295 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1105210 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1251711 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1335. Min Act: -0.0002

Data Index: 775643 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1180945 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1135. Min Act: -0.0002

Data Index: 950929 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1307. Min Act: -0.0002

Data Index: 485401 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1175. Min Act: -0.0001

Data Index: 139580 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1345. Min Act: -0.0001

Data Index: 360938 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1358. Min Act: -0.0002

Data Index: 487367 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1260. Min Act: -0.0002

Data Index: 455559 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1096974 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1212. Min Act: -0.0002

Data Index: 1099862 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1217. Min Act: -0.0002

Data Index: 334210 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1062180 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1319083 (C4 (Web Text))

Max Activating Token Index: 351