Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2929 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.5431. Min Act: -0.0000

Data Index: 94677 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.5189. Min Act: -0.0001

Data Index: 443398 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.5376. Min Act: -0.0001

Data Index: 478699 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.5147. Min Act: -0.0001

Data Index: 978922 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4709. Min Act: -0.0000

Data Index: 564148 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.5098. Min Act: -0.0001

Data Index: 85255 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4640. Min Act: -0.0001

Data Index: 178036 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1105930 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4775. Min Act: -0.0000

Data Index: 262942 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4727. Min Act: -0.0000

Data Index: 625101 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4689. Min Act: -0.0001

Data Index: 604726 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4485. Min Act: -0.0001

Data Index: 379443 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4346. Min Act: -0.0001

Data Index: 397428 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4548. Min Act: -0.0001

Data Index: 404518 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4576. Min Act: -0.0001

Data Index: 307621 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1158785 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4206. Min Act: -0.0000

Data Index: 826422 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4216. Min Act: -0.0001

Data Index: 536237 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4272. Min Act: -0.0001

Data Index: 1217924 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4416. Min Act: -0.0000

Data Index: 113924 (C4 (Web Text))

Max Activating Token Index: 862