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

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

Neuron 746 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.8355. Min Act: -0.0001

Data Index: 115920 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.8186. Min Act: -0.0001

Data Index: 670186 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1036902 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1423425 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7751. Min Act: -0.0001

Data Index: 1603388 (Python Code)

Max Activating Token Index: 800

Text #5

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7512. Min Act: -0.0001

Data Index: 987013 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7900. Min Act: -0.0001

Data Index: 661673 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1619760 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7582. Min Act: -0.0001

Data Index: 1407393 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7421. Min Act: -0.0001

Data Index: 1557674 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7458. Min Act: -0.0001

Data Index: 1455094 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7881. Min Act: -0.0001

Data Index: 376184 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7217. Min Act: -0.0001

Data Index: 278834 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7854. Min Act: -0.0001

Data Index: 810129 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7629. Min Act: -0.0001

Data Index: 371775 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7553. Min Act: -0.0001

Data Index: 1586604 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7746. Min Act: -0.0001

Data Index: 307740 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1058644 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7218. Min Act: -0.0001

Data Index: 225791 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7373. Min Act: -0.0001

Data Index: 1527564 (Python Code)

Max Activating Token Index: 18