Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2390 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4829. Min Act: -0.0001

Data Index: 964352 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4757. Min Act: -0.0001

Data Index: 486661 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4417. Min Act: -0.0001

Data Index: 22514 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4809. Min Act: -0.0001

Data Index: 58727 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4564. Min Act: -0.0001

Data Index: 1053718 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4671. Min Act: -0.0001

Data Index: 28349 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1064589 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4325. Min Act: -0.0001

Data Index: 687951 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4936. Min Act: -0.0001

Data Index: 218000 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4496. Min Act: -0.0001

Data Index: 788846 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4345. Min Act: -0.0001

Data Index: 669176 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4619. Min Act: -0.0001

Data Index: 358015 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4414. Min Act: -0.0001

Data Index: 229910 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4703. Min Act: -0.0001

Data Index: 1326257 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4127. Min Act: -0.0001

Data Index: 623742 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4344. Min Act: -0.0001

Data Index: 127830 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1253719 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4286. Min Act: -0.0001

Data Index: 932951 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4297. Min Act: -0.0001

Data Index: 1347995 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4382. Min Act: -0.0001

Data Index: 345731 (C4 (Web Text))

Max Activating Token Index: 40