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

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

Neuron 1608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.7881. Min Act: -0.0000

Data Index: 187104 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.7338. Min Act: -0.0000

Data Index: 113426 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.2140. Min Act: -0.0000

Data Index: 941539 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.3183. Min Act: -0.0000

Data Index: 189760 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.2471. Min Act: -0.0000

Data Index: 479498 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.0262. Min Act: -0.0000

Data Index: 469324 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.9210. Min Act: -0.0000

Data Index: 532236 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.0364. Min Act: -0.0000

Data Index: 790691 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 2.7881. Min Range: -2.7881

Max Act: 2.0861. Min Act: -0.0000

Data Index: 389209 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.8202. Min Act: -0.0000

Data Index: 920946 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.9250. Min Act: -0.0000

Data Index: 219379 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1020610 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.9283. Min Act: -0.0000

Data Index: 1072435 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.7383. Min Act: -0.0000

Data Index: 67264 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.7998. Min Act: -0.0000

Data Index: 447424 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.8091. Min Act: -0.0000

Data Index: 1082654 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.7891. Min Act: -0.0000

Data Index: 1061525 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.7716. Min Act: -0.0000

Data Index: 1147015 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.7576. Min Act: -0.0000

Data Index: 846673 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 2.7881. Min Range: -2.7881

Max Act: 1.7531. Min Act: -0.0000

Data Index: 913952 (C4 (Web Text))

Max Activating Token Index: 775