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

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

Neuron 3213 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1571620 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1391499 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2969. Min Act: -0.0001

Data Index: 1609988 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3090. Min Act: -0.0001

Data Index: 1655544 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1557401 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1458781 (Python Code)

Max Activating Token Index: 725

Text #6

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1636094 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1653055 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2358. Min Act: -0.0000

Data Index: 29281 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2402. Min Act: -0.0001

Data Index: 1367060 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1641304 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2294. Min Act: -0.0000

Data Index: 193240 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1470384 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2149. Min Act: -0.0000

Data Index: 71634 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2283. Min Act: -0.0001

Data Index: 1102624 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2252. Min Act: -0.0000

Data Index: 277113 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2165. Min Act: -0.0000

Data Index: 154341 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1634101 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2325. Min Act: -0.0001

Data Index: 1580708 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2236. Min Act: -0.0000

Data Index: 475548 (C4 (Web Text))

Max Activating Token Index: 579