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

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

Neuron 2444 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8186. Min Act: -0.0001

Data Index: 1461419 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.7222. Min Act: -0.0000

Data Index: 1454493 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8931. Min Act: -0.0000

Data Index: 1378337 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1500496 (Python Code)

Max Activating Token Index: 170

Text #4

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1380178 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1640748 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.6190. Min Act: -0.0000

Data Index: 1643344 (Python Code)

Max Activating Token Index: 308

Text #7

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.7548. Min Act: -0.0000

Data Index: 1403081 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.6741. Min Act: -0.0000

Data Index: 1577292 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.7281. Min Act: -0.0000

Data Index: 1444491 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1419896 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5491. Min Act: -0.0000

Data Index: 1556781 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.2512. Min Act: -0.0001

Data Index: 1626413 (Python Code)

Max Activating Token Index: 808

Text #13

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1390630 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5381. Min Act: -0.0001

Data Index: 1361065 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5148. Min Act: -0.0000

Data Index: 1458502 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1424701 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.2369. Min Act: -0.0001

Data Index: 1609061 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1540859 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.2386. Min Act: -0.0001

Data Index: 1363218 (Python Code)

Max Activating Token Index: 240