Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1902 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4440. Min Range: -4.4440

Max Act: 4.4440. Min Act: -0.0000

Data Index: 302960 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 4.4440. Min Range: -4.4440

Max Act: 4.0333. Min Act: -0.0000

Data Index: 87308 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 4.4440. Min Range: -4.4440

Max Act: 4.1520. Min Act: -0.0000

Data Index: 1169077 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.7215. Min Act: -0.0000

Data Index: 802730 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.5617. Min Act: -0.0000

Data Index: 1061862 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.8692. Min Act: -0.0000

Data Index: 1013022 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.8141. Min Act: -0.0000

Data Index: 664855 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.7655. Min Act: -0.0000

Data Index: 296973 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.5713. Min Act: -0.0000

Data Index: 987612 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.5812. Min Act: -0.0000

Data Index: 263639 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.5537. Min Act: -0.0000

Data Index: 22848 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.6544. Min Act: -0.0000

Data Index: 545326 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.4918. Min Act: -0.0000

Data Index: 604130 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.6209. Min Act: -0.0000

Data Index: 327582 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.6034. Min Act: -0.0000

Data Index: 493819 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.5566. Min Act: -0.0000

Data Index: 471560 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.3612. Min Act: -0.0000

Data Index: 399762 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.4729. Min Act: -0.0000

Data Index: 956772 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.4750. Min Act: -0.0000

Data Index: 1238593 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 4.4440. Min Range: -4.4440

Max Act: 3.4543. Min Act: -0.0000

Data Index: 891686 (C4 (Web Text))

Max Activating Token Index: 192