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

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

Neuron 4040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.8963. Min Act: -0.0000

Data Index: 1413109 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.7421. Min Act: -0.0000

Data Index: 1509485 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.8253. Min Act: -0.0000

Data Index: 1447647 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.5255. Min Act: -0.0000

Data Index: 1647950 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.5279. Min Act: -0.0000

Data Index: 1550045 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.6015. Min Act: -0.0000

Data Index: 1530042 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.6979. Min Act: -0.0000

Data Index: 1394399 (Python Code)

Max Activating Token Index: 856

Text #7

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.5751. Min Act: -0.0000

Data Index: 1625303 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.7225. Min Act: -0.0000

Data Index: 1552270 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.4452. Min Act: -0.0000

Data Index: 1409356 (Python Code)

Max Activating Token Index: 868

Text #10

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.6598. Min Act: -0.0000

Data Index: 1452226 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.5289. Min Act: -0.0000

Data Index: 1595754 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.4941. Min Act: -0.0000

Data Index: 1399469 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.5873. Min Act: -0.0000

Data Index: 1599478 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.3317. Min Act: -0.0000

Data Index: 1388468 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.4392. Min Act: -0.0000

Data Index: 1448423 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.4436. Min Act: -0.0000

Data Index: 1600795 (Python Code)

Max Activating Token Index: 256

Text #17

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.3179. Min Act: -0.0000

Data Index: 1632015 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.4256. Min Act: -0.0000

Data Index: 1555131 (Python Code)

Max Activating Token Index: 699

Text #19

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.4236. Min Act: -0.0000

Data Index: 1627462 (Python Code)

Max Activating Token Index: 189