Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 546 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7283. Min Act: -0.0001

Data Index: 443115 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7642. Min Act: -0.0001

Data Index: 788539 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7405. Min Act: -0.0001

Data Index: 1222205 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6909. Min Act: -0.0001

Data Index: 814893 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7177. Min Act: -0.0001

Data Index: 147982 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1072688 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5949. Min Act: -0.0001

Data Index: 127710 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6030. Min Act: -0.0001

Data Index: 1271392 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5852. Min Act: -0.0001

Data Index: 682933 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5830. Min Act: -0.0001

Data Index: 876728 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5618. Min Act: -0.0001

Data Index: 202971 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6112. Min Act: -0.0001

Data Index: 316420 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5704. Min Act: -0.0001

Data Index: 348266 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5432. Min Act: -0.0001

Data Index: 496563 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5482. Min Act: -0.0001

Data Index: 141461 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5627. Min Act: -0.0001

Data Index: 387409 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5438. Min Act: -0.0001

Data Index: 1144557 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4862. Min Act: -0.0001

Data Index: 469520 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4426. Min Act: -0.0001

Data Index: 1028930 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5323. Min Act: -0.0001

Data Index: 555444 (C4 (Web Text))

Max Activating Token Index: 128