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

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

Neuron 660 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5642. Min Act: -0.0001

Data Index: 304752 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4787. Min Act: -0.0001

Data Index: 508053 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4865. Min Act: -0.0001

Data Index: 523700 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1213388 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4785. Min Act: -0.0001

Data Index: 707300 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4924. Min Act: -0.0001

Data Index: 182407 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4281. Min Act: -0.0001

Data Index: 1331667 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4625. Min Act: -0.0001

Data Index: 838323 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4345. Min Act: -0.0001

Data Index: 759462 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4443. Min Act: -0.0001

Data Index: 460514 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4419. Min Act: -0.0001

Data Index: 601662 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4385. Min Act: -0.0001

Data Index: 59604 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4409. Min Act: -0.0001

Data Index: 627942 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4440. Min Act: -0.0001

Data Index: 301379 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4592. Min Act: -0.0001

Data Index: 637369 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4274. Min Act: -0.0001

Data Index: 1348754 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4028. Min Act: -0.0001

Data Index: 1070420 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4164. Min Act: -0.0001

Data Index: 385441 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4128. Min Act: -0.0001

Data Index: 727203 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4245. Min Act: -0.0001

Data Index: 723688 (C4 (Web Text))

Max Activating Token Index: 481