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

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

Neuron 218 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1783. Min Act: -0.0000

Data Index: 936715 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1697. Min Act: -0.0001

Data Index: 602550 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1632. Min Act: -0.0000

Data Index: 630132 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1670. Min Act: -0.0001

Data Index: 54892 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1605. Min Act: -0.0000

Data Index: 868763 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1479. Min Act: -0.0001

Data Index: 950298 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1426. Min Act: -0.0000

Data Index: 960919 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1367. Min Act: -0.0000

Data Index: 727423 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1315244 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1265914 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1327942 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1318. Min Act: -0.0000

Data Index: 607661 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1250320 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1320. Min Act: -0.0000

Data Index: 31245 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1321. Min Act: -0.0000

Data Index: 693447 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1319. Min Act: -0.0000

Data Index: 170242 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1389. Min Act: -0.0001

Data Index: 884041 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1247. Min Act: -0.0001

Data Index: 524852 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1277. Min Act: -0.0000

Data Index: 933338 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1278. Min Act: -0.0000

Data Index: 117530 (C4 (Web Text))

Max Activating Token Index: 808