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

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

Neuron 2641 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2273. Min Range: -2.2273

Max Act: 2.2273. Min Act: -0.0000

Data Index: 697640 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.8769. Min Act: -0.0000

Data Index: 674001 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6863. Min Act: -0.0000

Data Index: 641206 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6617. Min Act: -0.0000

Data Index: 544614 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6954. Min Act: -0.0000

Data Index: 599010 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.8040. Min Act: -0.0000

Data Index: 352745 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6925. Min Act: -0.0000

Data Index: 1221271 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6576. Min Act: -0.0000

Data Index: 909566 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1153505 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1240368 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6033. Min Act: -0.0000

Data Index: 827739 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.6028. Min Act: -0.0000

Data Index: 134351 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.4757. Min Act: -0.0000

Data Index: 914709 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.5788. Min Act: -0.0000

Data Index: 252329 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.5750. Min Act: -0.0000

Data Index: 262056 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.5529. Min Act: -0.0000

Data Index: 752073 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.4676. Min Act: -0.0000

Data Index: 656571 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.5356. Min Act: -0.0000

Data Index: 138263 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1098400 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 2.2273. Min Range: -2.2273

Max Act: 1.4307. Min Act: -0.0000

Data Index: 1075501 (C4 (Web Text))

Max Activating Token Index: 301