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

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

Neuron 36 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0003

Data Index: 869296 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0305. Min Act: -0.0003

Data Index: 279347 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1268883 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0278. Min Act: -0.0003

Data Index: 385129 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0282. Min Act: -0.0003

Data Index: 522010 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0286. Min Act: -0.0003

Data Index: 121796 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0286. Min Act: -0.0003

Data Index: 47346 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1220428 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0257. Min Act: -0.0003

Data Index: 554388 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0275. Min Act: -0.0003

Data Index: 976494 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1329669 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0264. Min Act: -0.0003

Data Index: 694252 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0267. Min Act: -0.0002

Data Index: 485721 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1047923 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0259. Min Act: -0.0003

Data Index: 563081 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1167304 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1041083 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1158792 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0254. Min Act: -0.0003

Data Index: 642347 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1265685 (C4 (Web Text))

Max Activating Token Index: 466