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

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

Neuron 3 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: 3.9475. Min Range: -3.9475

Max Act: 3.9475. Min Act: -0.0000

Data Index: 506364 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 3.9475. Min Range: -3.9475

Max Act: 3.6145. Min Act: -0.0000

Data Index: 764329 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 3.9475. Min Range: -3.9475

Max Act: 3.7352. Min Act: -0.0000

Data Index: 1251758 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 3.9475. Min Range: -3.9475

Max Act: 3.2934. Min Act: -0.0000

Data Index: 1034531 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 3.9475. Min Range: -3.9475

Max Act: 3.0459. Min Act: -0.0000

Data Index: 41630 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 3.9475. Min Range: -3.9475

Max Act: 3.1755. Min Act: -0.0000

Data Index: 611507 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.8924. Min Act: -0.0001

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.9772. Min Act: -0.0000

Data Index: 157311 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.7778. Min Act: -0.0000

Data Index: 953426 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.7398. Min Act: -0.0001

Data Index: 1346908 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.8756. Min Act: -0.0000

Data Index: 1275276 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.8605. Min Act: -0.0000

Data Index: 513257 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.8540. Min Act: -0.0000

Data Index: 214941 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.7024. Min Act: -0.0000

Data Index: 1330766 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.6441. Min Act: -0.0000

Data Index: 193756 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.6246. Min Act: -0.0000

Data Index: 830541 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.8924. Min Act: -0.0000

Data Index: 1210236 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.7394. Min Act: -0.0000

Data Index: 1291578 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.7233. Min Act: -0.0001

Data Index: 69590 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.9475. Min Range: -3.9475

Max Act: 2.8280. Min Act: -0.0000

Data Index: 255862 (C4 (Web Text))

Max Activating Token Index: 877