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

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

Neuron 1005 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: 1.5511. Min Range: -1.5511

Max Act: 1.5420. Min Act: -0.0001

Data Index: 1636090 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.4742. Min Act: -0.0001

Data Index: 802430 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.5511. Min Act: -0.0001

Data Index: 1599118 (Python Code)

Max Activating Token Index: 999

Text #3

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.4491. Min Act: -0.0001

Data Index: 23502 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.4162. Min Act: -0.0001

Data Index: 748343 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3326. Min Act: -0.0001

Data Index: 348938 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3832. Min Act: -0.0001

Data Index: 1476237 (Python Code)

Max Activating Token Index: 60

Text #7

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3051. Min Act: -0.0001

Data Index: 1617129 (Python Code)

Max Activating Token Index: 259

Text #8

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3771. Min Act: -0.0001

Data Index: 1457839 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3055. Min Act: -0.0001

Data Index: 1365873 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3365. Min Act: -0.0001

Data Index: 443767 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.2860. Min Act: -0.0001

Data Index: 299106 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3205. Min Act: -0.0001

Data Index: 1643345 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3224. Min Act: -0.0001

Data Index: 1384394 (Python Code)

Max Activating Token Index: 579

Text #14

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3572. Min Act: -0.0001

Data Index: 347671 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3243. Min Act: -0.0001

Data Index: 635204 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3112. Min Act: -0.0001

Data Index: 420972 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3552. Min Act: -0.0001

Data Index: 664751 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.2909. Min Act: -0.0001

Data Index: 1150001 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3022. Min Act: -0.0001

Data Index: 1429414 (Python Code)

Max Activating Token Index: 612