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

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

Neuron 1924 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5991. Min Act: -0.0002

Data Index: 327860 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.6448. Min Act: -0.0002

Data Index: 611907 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.6296. Min Act: -0.0002

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5942. Min Act: -0.0002

Data Index: 1355257 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.6171. Min Act: -0.0002

Data Index: 1114536 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5823. Min Act: -0.0002

Data Index: 94418 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5973. Min Act: -0.0002

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5409. Min Act: -0.0002

Data Index: 1134005 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5906. Min Act: -0.0002

Data Index: 254373 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.6130. Min Act: -0.0002

Data Index: 1260939 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5264. Min Act: -0.0002

Data Index: 670174 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5532. Min Act: -0.0002

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5580. Min Act: -0.0002

Data Index: 129694 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5549. Min Act: -0.0002

Data Index: 701197 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5369. Min Act: -0.0002

Data Index: 493281 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5358. Min Act: -0.0002

Data Index: 1229754 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5344. Min Act: -0.0002

Data Index: 901503 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.4865. Min Act: -0.0002

Data Index: 1309785 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5469. Min Act: -0.0002

Data Index: 1175642 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5422. Min Act: -0.0002

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 774