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

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

Neuron 4400 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2313. Min Act: -0.0001

Data Index: 1149469 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1930. Min Act: -0.0001

Data Index: 880252 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1672. Min Act: -0.0001

Data Index: 652734 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1728. Min Act: -0.0001

Data Index: 532833 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1305376 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1739. Min Act: -0.0001

Data Index: 693449 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1525. Min Act: -0.0001

Data Index: 304813 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1575. Min Act: -0.0001

Data Index: 396901 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1651. Min Act: -0.0001

Data Index: 192434 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1388. Min Act: -0.0001

Data Index: 917862 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1353. Min Act: -0.0001

Data Index: 212559 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1453. Min Act: -0.0001

Data Index: 509303 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1380. Min Act: -0.0001

Data Index: 251523 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1136125 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1358163 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1103004 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1405. Min Act: -0.0001

Data Index: 200743 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1153969 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1151778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1296. Min Act: -0.0001

Data Index: 931184 (C4 (Web Text))

Max Activating Token Index: 852