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

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

Neuron 3268 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: 0.6851. Min Range: -0.6851

Max Act: 0.6851. Min Act: -0.0000

Data Index: 499210 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5819. Min Act: -0.0000

Data Index: 18394 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1223939 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5174. Min Act: -0.0000

Data Index: 608788 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1328133 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1167484 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5019. Min Act: -0.0000

Data Index: 328605 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4961. Min Act: -0.0000

Data Index: 177154 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5149. Min Act: -0.0000

Data Index: 360022 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1066112 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5105. Min Act: -0.0000

Data Index: 83196 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4697. Min Act: -0.0000

Data Index: 411456 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4776. Min Act: -0.0000

Data Index: 353512 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1353694 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4634. Min Act: -0.0000

Data Index: 134475 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1298738 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4644. Min Act: -0.0000

Data Index: 523128 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1154878 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4643. Min Act: -0.0000

Data Index: 214485 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4451. Min Act: -0.0000

Data Index: 897486 (C4 (Web Text))

Max Activating Token Index: 541