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

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

Neuron 2353 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: 1.1332. Min Range: -1.1332

Max Act: 1.1332. Min Act: -0.0000

Data Index: 740827 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1211104 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.1332. Min Range: -1.1332

Max Act: 1.0229. Min Act: -0.0000

Data Index: 136277 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1125328 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8652. Min Act: -0.0000

Data Index: 548997 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1062304 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.9035. Min Act: -0.0000

Data Index: 325548 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.9255. Min Act: -0.0000

Data Index: 757681 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8726. Min Act: -0.0000

Data Index: 378534 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1164730 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8404. Min Act: -0.0000

Data Index: 511429 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8513. Min Act: -0.0000

Data Index: 858596 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8348. Min Act: -0.0000

Data Index: 87722 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.7209. Min Act: -0.0000

Data Index: 519669 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.8214. Min Act: -0.0000

Data Index: 312997 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.6871. Min Act: -0.0000

Data Index: 504104 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1264645 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.6171. Min Act: -0.0000

Data Index: 645942 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1250674 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 1.1332. Min Range: -1.1332

Max Act: 0.6015. Min Act: -0.0000

Data Index: 265012 (C4 (Web Text))

Max Activating Token Index: 137