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

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

Neuron 4568 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1820. Min Range: -4.1820

Max Act: 4.1820. Min Act: -0.0000

Data Index: 483947 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.8524. Min Act: -0.0000

Data Index: 759806 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.8083. Min Act: -0.0000

Data Index: 823680 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.7464. Min Act: -0.0000

Data Index: 1053944 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.7261. Min Act: -0.0000

Data Index: 1329583 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.5341. Min Act: -0.0000

Data Index: 548961 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.6698. Min Act: -0.0000

Data Index: 54840 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.6457. Min Act: -0.0000

Data Index: 6987 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.6339. Min Act: -0.0000

Data Index: 129487 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.4745. Min Act: -0.0000

Data Index: 290733 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.4494. Min Act: -0.0000

Data Index: 827167 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.4604. Min Act: -0.0000

Data Index: 412845 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.4707. Min Act: -0.0000

Data Index: 539183 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.6077. Min Act: -0.0000

Data Index: 102428 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.4301. Min Act: -0.0000

Data Index: 1062105 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.6141. Min Act: -0.0000

Data Index: 584609 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.6022. Min Act: -0.0000

Data Index: 533354 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.5842. Min Act: -0.0000

Data Index: 1203346 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.5862. Min Act: -0.0000

Data Index: 861865 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 4.1820. Min Range: -4.1820

Max Act: 3.5628. Min Act: -0.0000

Data Index: 166870 (C4 (Web Text))

Max Activating Token Index: 23