Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 284 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0433. Min Act: -0.0001

Data Index: 577948 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0002

Data Index: 775275 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1319087 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0436. Min Act: -0.0002

Data Index: 665192 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0420. Min Act: -0.0002

Data Index: 945148 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0451. Min Act: -0.0001

Data Index: 2764 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0495. Min Act: -0.0001

Data Index: 146112 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1029905 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0448. Min Act: -0.0002

Data Index: 137807 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1122324 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1089157 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0372. Min Act: -0.0001

Data Index: 808073 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0382. Min Act: -0.0001

Data Index: 442387 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1146029 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0413. Min Act: -0.0001

Data Index: 98243 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0382. Min Act: -0.0001

Data Index: 185648 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0366. Min Act: -0.0002

Data Index: 90160 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1246133 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0393. Min Act: -0.0001

Data Index: 192933 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1249718 (C4 (Web Text))

Max Activating Token Index: 35