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

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

Neuron 3844 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0002

Data Index: 502571 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0485. Min Act: -0.0002

Data Index: 703084 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0480. Min Act: -0.0002

Data Index: 859472 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0477. Min Act: -0.0002

Data Index: 141559 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0443. Min Act: -0.0002

Data Index: 343304 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0458. Min Act: -0.0002

Data Index: 19060 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1013901 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0429. Min Act: -0.0002

Data Index: 995181 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0429. Min Act: -0.0002

Data Index: 579736 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0421. Min Act: -0.0002

Data Index: 63725 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1256342 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1261158 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0433. Min Act: -0.0002

Data Index: 656709 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0423. Min Act: -0.0002

Data Index: 383423 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1150165 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0414. Min Act: -0.0002

Data Index: 714259 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0400. Min Act: -0.0002

Data Index: 9321 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1103570 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0412. Min Act: -0.0002

Data Index: 238996 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0394. Min Act: -0.0002

Data Index: 180001 (C4 (Web Text))

Max Activating Token Index: 833