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

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

Neuron 2655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4582. Min Act: -0.0000

Data Index: 26044 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4690. Min Act: -0.0000

Data Index: 821517 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1072199 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4248. Min Act: -0.0000

Data Index: 667357 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1091070 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4153. Min Act: -0.0000

Data Index: 67973 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4114. Min Act: -0.0000

Data Index: 746193 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1232027 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3868. Min Act: -0.0000

Data Index: 357850 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3923. Min Act: -0.0000

Data Index: 626913 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1148971 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3898. Min Act: -0.0001

Data Index: 55233 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3865. Min Act: -0.0000

Data Index: 802740 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3733. Min Act: -0.0000

Data Index: 243463 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3842. Min Act: -0.0000

Data Index: 684953 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1142625 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3825. Min Act: -0.0000

Data Index: 617948 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3777. Min Act: -0.0000

Data Index: 446889 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3465. Min Act: -0.0000

Data Index: 624294 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3356. Min Act: -0.0001

Data Index: 903975 (C4 (Web Text))

Max Activating Token Index: 792