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

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

Neuron 228 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.9773. Min Act: -0.0001

Data Index: 821655 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8516. Min Act: -0.0001

Data Index: 1122732 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.9333. Min Act: -0.0001

Data Index: 376209 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8936. Min Act: -0.0002

Data Index: 189958 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8622. Min Act: -0.0002

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8745. Min Act: -0.0001

Data Index: 746595 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8604. Min Act: -0.0001

Data Index: 884832 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8202. Min Act: -0.0001

Data Index: 454037 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.9282. Min Act: -0.0001

Data Index: 1239000 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8641. Min Act: -0.0002

Data Index: 1024023 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8888. Min Act: -0.0001

Data Index: 386479 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8232. Min Act: -0.0002

Data Index: 1095289 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8097. Min Act: -0.0001

Data Index: 346668 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8321. Min Act: -0.0001

Data Index: 928612 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8234. Min Act: -0.0002

Data Index: 1326293 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7546. Min Act: -0.0002

Data Index: 547875 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7457. Min Act: -0.0001

Data Index: 330592 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8033. Min Act: -0.0002

Data Index: 771869 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8328. Min Act: -0.0001

Data Index: 419683 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8057. Min Act: -0.0002

Data Index: 622506 (C4 (Web Text))

Max Activating Token Index: 644