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

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

Neuron 3145 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: 0.1772. Min Range: -0.1772

Max Act: 0.1772. Min Act: -0.0001

Data Index: 533984 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1483. Min Act: -0.0000

Data Index: 898689 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1268658 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1515. Min Act: -0.0000

Data Index: 620907 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1170043 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1329. Min Act: -0.0000

Data Index: 126051 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1324. Min Act: -0.0000

Data Index: 458902 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1319. Min Act: -0.0000

Data Index: 57479 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1595829 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1057069 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1270. Min Act: -0.0000

Data Index: 171147 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1157. Min Act: -0.0000

Data Index: 717286 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1208. Min Act: -0.0000

Data Index: 20647 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1188. Min Act: -0.0000

Data Index: 386186 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1214. Min Act: -0.0000

Data Index: 73134 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1169. Min Act: -0.0000

Data Index: 960062 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1168. Min Act: -0.0000

Data Index: 294195 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1337215 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1109. Min Act: -0.0000

Data Index: 29429 (C4 (Web Text))

Max Activating Token Index: 539