Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4148 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1581372 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1524894 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1623440 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1422419 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3789. Min Act: -0.0000

Data Index: 187480 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3416. Min Act: -0.0000

Data Index: 184878 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1461972 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3557. Min Act: -0.0000

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1387848 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1427845 (Python Code)

Max Activating Token Index: 644

Text #11

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1515808 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1361637 (Python Code)

Max Activating Token Index: 78

Text #13

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1609466 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1472334 (Python Code)

Max Activating Token Index: 192

Text #15

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3370. Min Act: -0.0000

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3661. Min Act: -0.0000

Data Index: 700534 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1381593 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1634049 (Python Code)

Max Activating Token Index: 872

Text #19

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3283. Min Act: -0.0000

Data Index: 801545 (C4 (Web Text))

Max Activating Token Index: 571