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

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

Neuron 848 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4395. Min Range: -4.4395

Max Act: 4.4395. Min Act: -0.0000

Data Index: 1012657 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.8686. Min Act: -0.0000

Data Index: 1313102 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 4.4395. Min Range: -4.4395

Max Act: 4.0255. Min Act: -0.0000

Data Index: 102580 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.6772. Min Act: -0.0000

Data Index: 370758 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.7881. Min Act: -0.0000

Data Index: 1282623 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.5799. Min Act: -0.0000

Data Index: 760158 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.3214. Min Act: -0.0000

Data Index: 675506 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.6417. Min Act: -0.0000

Data Index: 1237119 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.2735. Min Act: -0.0000

Data Index: 1339287 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.2776. Min Act: -0.0000

Data Index: 1103709 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.1778. Min Act: -0.0000

Data Index: 757549 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.1627. Min Act: -0.0000

Data Index: 1178723 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.1621. Min Act: -0.0000

Data Index: 196368 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.1389. Min Act: -0.0000

Data Index: 250129 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 4.4395. Min Range: -4.4395

Max Act: 2.9704. Min Act: -0.0000

Data Index: 823471 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.0921. Min Act: -0.0000

Data Index: 1201248 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.2370. Min Act: -0.0000

Data Index: 296044 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 4.4395. Min Range: -4.4395

Max Act: 2.9585. Min Act: -0.0000

Data Index: 315810 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 4.4395. Min Range: -4.4395

Max Act: 2.9360. Min Act: -0.0000

Data Index: 213906 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 4.4395. Min Range: -4.4395

Max Act: 3.0565. Min Act: -0.0000

Data Index: 173206 (C4 (Web Text))

Max Activating Token Index: 418