Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4675 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1678. Min Act: -0.0002

Data Index: 450544 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1609. Min Act: -0.0002

Data Index: 862195 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1249. Min Act: -0.0002

Data Index: 1195030 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1423. Min Act: -0.0002

Data Index: 933370 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1382. Min Act: -0.0003

Data Index: 1020883 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1450. Min Act: -0.0002

Data Index: 216887 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1313. Min Act: -0.0002

Data Index: 584661 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1163782 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1347. Min Act: -0.0002

Data Index: 497136 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1311. Min Act: -0.0002

Data Index: 311234 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1388. Min Act: -0.0002

Data Index: 790305 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1241. Min Act: -0.0002

Data Index: 629282 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1325. Min Act: -0.0002

Data Index: 148416 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1320. Min Act: -0.0002

Data Index: 143784 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1303. Min Act: -0.0002

Data Index: 212262 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1387. Min Act: -0.0002

Data Index: 1269066 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1269376 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1073. Min Act: -0.0002

Data Index: 753441 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1469. Min Act: -0.0002

Data Index: 314755 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1266. Min Act: -0.0002

Data Index: 884148 (C4 (Web Text))

Max Activating Token Index: 407