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

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

Neuron 3206 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4642. Min Range: -3.4642

Max Act: 3.4642. Min Act: -0.0000

Data Index: 435799 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.9436. Min Act: -0.0000

Data Index: 734266 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.9735. Min Act: -0.0000

Data Index: 864231 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.5912. Min Act: -0.0000

Data Index: 162176 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.5006. Min Act: -0.0000

Data Index: 619277 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.6315. Min Act: -0.0000

Data Index: 1220275 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.5939. Min Act: -0.0000

Data Index: 763929 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.5499. Min Act: -0.0000

Data Index: 355208 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.4836. Min Act: -0.0000

Data Index: 1039964 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.3529. Min Act: -0.0000

Data Index: 219772 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.4164. Min Act: -0.0000

Data Index: 1158329 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.3366. Min Act: -0.0000

Data Index: 362821 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.1758. Min Act: -0.0000

Data Index: 135403 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.2705. Min Act: -0.0000

Data Index: 326819 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 3.4642. Min Range: -3.4642

Max Act: 1.8868. Min Act: -0.0000

Data Index: 252960 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.1037. Min Act: -0.0000

Data Index: 833250 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.0890. Min Act: -0.0000

Data Index: 704485 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.0812. Min Act: -0.0000

Data Index: 186468 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.0645. Min Act: -0.0000

Data Index: 169797 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.4642. Min Range: -3.4642

Max Act: 2.0375. Min Act: -0.0000

Data Index: 909216 (C4 (Web Text))

Max Activating Token Index: 508