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

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

Neuron 2312 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1866. Min Act: -0.0002

Data Index: 992274 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1659. Min Act: -0.0002

Data Index: 1016197 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1625. Min Act: -0.0003

Data Index: 360129 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1614. Min Act: -0.0002

Data Index: 1350521 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1591. Min Act: -0.0003

Data Index: 649224 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1540. Min Act: -0.0002

Data Index: 637601 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1466. Min Act: -0.0002

Data Index: 906628 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1453. Min Act: -0.0002

Data Index: 339311 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1380. Min Act: -0.0002

Data Index: 499303 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1339. Min Act: -0.0002

Data Index: 364969 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1331. Min Act: -0.0002

Data Index: 678113 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1328. Min Act: -0.0002

Data Index: 898283 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1370. Min Act: -0.0002

Data Index: 88161 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1319. Min Act: -0.0003

Data Index: 88590 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1317. Min Act: -0.0002

Data Index: 204963 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1312. Min Act: -0.0002

Data Index: 1541172 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1311. Min Act: -0.0002

Data Index: 955259 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1302. Min Act: -0.0002

Data Index: 884974 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1293. Min Act: -0.0002

Data Index: 699810 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1291. Min Act: -0.0003

Data Index: 953088 (C4 (Web Text))

Max Activating Token Index: 181