Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2335 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7494. Min Act: -0.0000

Data Index: 1334990 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.5793. Min Act: -0.0000

Data Index: 252339 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6236. Min Act: -0.0000

Data Index: 111211 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.5855. Min Act: -0.0000

Data Index: 868171 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3387. Min Act: -0.0000

Data Index: 921189 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.4441. Min Act: -0.0000

Data Index: 840444 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.4729. Min Act: -0.0000

Data Index: 879377 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1083564 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6189. Min Act: -0.0000

Data Index: 255373 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1046472 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3952. Min Act: -0.0000

Data Index: 954600 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3235. Min Act: -0.0000

Data Index: 157513 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1192523 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3334. Min Act: -0.0000

Data Index: 374294 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3759. Min Act: -0.0000

Data Index: 301833 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.2649. Min Act: -0.0000

Data Index: 219436 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1037928 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.2294. Min Act: -0.0000

Data Index: 375467 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.1300. Min Act: -0.0000

Data Index: 366571 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1215649 (C4 (Web Text))

Max Activating Token Index: 563