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

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

Neuron 4626 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1487. Min Act: -0.0000

Data Index: 696292 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1440. Min Act: -0.0000

Data Index: 816271 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1391. Min Act: 0.0000

Data Index: 1018429 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1347. Min Act: -0.0000

Data Index: 494378 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1303160 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1256. Min Act: -0.0000

Data Index: 832531 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1163479 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1268. Min Act: -0.0000

Data Index: 364082 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1278. Min Act: -0.0000

Data Index: 23226 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1298. Min Act: 0.0000

Data Index: 160200 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1246. Min Act: -0.0000

Data Index: 670345 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1284. Min Act: -0.0000

Data Index: 709409 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1191. Min Act: -0.0000

Data Index: 946092 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1188. Min Act: -0.0000

Data Index: 51764 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1153. Min Act: -0.0000

Data Index: 675701 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1187. Min Act: -0.0000

Data Index: 764300 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1209. Min Act: -0.0000

Data Index: 533238 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1160. Min Act: 0.0000

Data Index: 1229602 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1150. Min Act: 0.0000

Data Index: 985452 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1091. Min Act: 0.0000

Data Index: 421378 (C4 (Web Text))

Max Activating Token Index: 546