Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 434 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.5207. Min Act: -0.0003

Data Index: 893184 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4485. Min Act: -0.0003

Data Index: 467306 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4225. Min Act: -0.0003

Data Index: 202329 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4130. Min Act: -0.0004

Data Index: 734675 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4117. Min Act: -0.0003

Data Index: 1235860 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3956. Min Act: -0.0003

Data Index: 1194970 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4000. Min Act: -0.0003

Data Index: 787010 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3804. Min Act: -0.0004

Data Index: 308658 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3970. Min Act: -0.0003

Data Index: 507993 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3931. Min Act: -0.0003

Data Index: 706717 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3852. Min Act: -0.0003

Data Index: 301077 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3815. Min Act: -0.0003

Data Index: 906459 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3843. Min Act: -0.0003

Data Index: 996630 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3917. Min Act: -0.0004

Data Index: 9431 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3861. Min Act: -0.0003

Data Index: 435745 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3910. Min Act: -0.0003

Data Index: 59926 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3865. Min Act: -0.0003

Data Index: 1122144 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3710. Min Act: -0.0003

Data Index: 756557 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3738. Min Act: -0.0004

Data Index: 801240 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3832. Min Act: -0.0003

Data Index: 187153 (C4 (Web Text))

Max Activating Token Index: 207