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

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

Neuron 65 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9481. Min Act: -0.0001

Data Index: 177516 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9454. Min Act: -0.0001

Data Index: 115828 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9486. Min Act: -0.0001

Data Index: 1250581 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1048687 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9474. Min Act: -0.0001

Data Index: 1578339 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9382. Min Act: -0.0000

Data Index: 396745 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9381. Min Act: -0.0001

Data Index: 553580 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8890. Min Act: -0.0001

Data Index: 365724 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9143. Min Act: -0.0001

Data Index: 505151 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1132184 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1014443 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8421. Min Act: -0.0000

Data Index: 405505 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8996. Min Act: -0.0001

Data Index: 577690 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9059. Min Act: -0.0001

Data Index: 93474 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8791. Min Act: -0.0001

Data Index: 1251554 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8225. Min Act: -0.0001

Data Index: 80102 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8521. Min Act: -0.0001

Data Index: 823937 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8479. Min Act: -0.0000

Data Index: 927624 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8432. Min Act: -0.0001

Data Index: 1058764 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8454. Min Act: -0.0001

Data Index: 376946 (C4 (Web Text))

Max Activating Token Index: 528