Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3724 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.9568. Min Act: -0.0001

Data Index: 278082 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 1.0361. Min Range: -1.0361

Max Act: 1.0361. Min Act: -0.0001

Data Index: 752765 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.6607. Min Act: -0.0001

Data Index: 74951 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.3269. Min Act: -0.0001

Data Index: 1287491 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1066219 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.2006. Min Act: -0.0000

Data Index: 819308 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1263978 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1994. Min Act: -0.0000

Data Index: 906738 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1670. Min Act: -0.0000

Data Index: 328978 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1488176 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1005629 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1567. Min Act: -0.0000

Data Index: 319818 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1375206 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1608. Min Act: -0.0000

Data Index: 424598 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1444. Min Act: -0.0000

Data Index: 967965 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1223. Min Act: -0.0000

Data Index: 551602 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1445. Min Act: -0.0000

Data Index: 420459 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1394. Min Act: -0.0001

Data Index: 226201 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1085027 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.1361. Min Act: -0.0000

Data Index: 545266 (C4 (Web Text))

Max Activating Token Index: 426