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

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

Neuron 2219 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.9332. Min Act: -0.0001

Data Index: 504327 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.8439. Min Act: -0.0001

Data Index: 33692 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.8622. Min Act: -0.0001

Data Index: 953315 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.7126. Min Act: -0.0001

Data Index: 573824 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.7153. Min Act: -0.0001

Data Index: 167501 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.7336. Min Act: -0.0001

Data Index: 377650 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.7432. Min Act: -0.0001

Data Index: 922911 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.7444. Min Act: -0.0001

Data Index: 662450 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6870. Min Act: -0.0001

Data Index: 849303 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1150330 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6690. Min Act: -0.0001

Data Index: 1338003 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6871. Min Act: -0.0001

Data Index: 894953 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6425. Min Act: -0.0001

Data Index: 1083527 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6431. Min Act: -0.0001

Data Index: 52209 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6572. Min Act: -0.0001

Data Index: 837814 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6258. Min Act: -0.0001

Data Index: 782297 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6610. Min Act: -0.0001

Data Index: 441741 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1159449 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6292. Min Act: -0.0001

Data Index: 307615 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.9332. Min Range: -0.9332

Max Act: 0.6181. Min Act: -0.0001

Data Index: 148762 (C4 (Web Text))

Max Activating Token Index: 338