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

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

Neuron 3461 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: 1.4868. Min Range: -1.4868

Max Act: 1.4868. Min Act: -0.0000

Data Index: 493224 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.4208. Min Act: -0.0001

Data Index: 152728 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.2967. Min Act: -0.0001

Data Index: 572476 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1326465 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.3202. Min Act: -0.0001

Data Index: 1595997 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1816. Min Act: -0.0001

Data Index: 947124 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.2018. Min Act: -0.0001

Data Index: 403483 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1679. Min Act: -0.0001

Data Index: 1385245 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1325303 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.2021. Min Act: -0.0001

Data Index: 23853 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1937. Min Act: -0.0001

Data Index: 1205772 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1305301 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.0530. Min Act: -0.0000

Data Index: 183578 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1364. Min Act: -0.0001

Data Index: 1429707 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.0829. Min Act: -0.0001

Data Index: 1646258 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.2025. Min Act: -0.0001

Data Index: 970208 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1176071 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.0628. Min Act: -0.0000

Data Index: 65726 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1400525 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1197. Min Act: -0.0001

Data Index: 1346362 (C4 (Web Text))

Max Activating Token Index: 862