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

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

Neuron 3108 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.7309. Min Act: -0.0001

Data Index: 738779 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.6208. Min Act: -0.0001

Data Index: 974246 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.7034. Min Act: -0.0001

Data Index: 720918 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.4916. Min Act: -0.0001

Data Index: 736332 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.5652. Min Act: -0.0001

Data Index: 730537 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.6729. Min Act: -0.0001

Data Index: 1280005 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.6067. Min Act: -0.0001

Data Index: 560530 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.7890. Min Act: -0.0001

Data Index: 865394 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.5544. Min Act: -0.0001

Data Index: 1162575 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.6505. Min Act: -0.0001

Data Index: 215897 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.5207. Min Act: -0.0001

Data Index: 212689 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.4302. Min Act: -0.0001

Data Index: 279365 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.5417. Min Act: -0.0001

Data Index: 55105 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.4801. Min Act: -0.0001

Data Index: 1017655 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.6380. Min Act: -0.0001

Data Index: 374534 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.5025. Min Act: -0.0001

Data Index: 171611 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.4335. Min Act: -0.0001

Data Index: 297601 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.4379. Min Act: -0.0001

Data Index: 330453 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.5044. Min Act: -0.0001

Data Index: 590509 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.4484. Min Act: -0.0001

Data Index: 506492 (C4 (Web Text))

Max Activating Token Index: 66