Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 819 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1651. Min Act: -0.0002

Data Index: 472753 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1422. Min Act: -0.0002

Data Index: 988352 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1439. Min Act: -0.0002

Data Index: 1136907 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1453. Min Act: -0.0002

Data Index: 416427 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1424. Min Act: -0.0002

Data Index: 444677 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1401. Min Act: -0.0002

Data Index: 1231429 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1397. Min Act: -0.0002

Data Index: 462117 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1388. Min Act: -0.0002

Data Index: 885229 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1385. Min Act: -0.0002

Data Index: 725841 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1372. Min Act: -0.0002

Data Index: 32312 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1382. Min Act: -0.0002

Data Index: 702974 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1371. Min Act: -0.0002

Data Index: 436070 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1329. Min Act: -0.0002

Data Index: 946501 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1324. Min Act: -0.0002

Data Index: 996976 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1325. Min Act: -0.0002

Data Index: 903324 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1322. Min Act: -0.0002

Data Index: 973925 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1305. Min Act: -0.0002

Data Index: 138035 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1253. Min Act: -0.0002

Data Index: 996952 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1300. Min Act: -0.0002

Data Index: 1616823 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1302. Min Act: -0.0002

Data Index: 958344 (C4 (Web Text))

Max Activating Token Index: 739