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

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

Neuron 3598 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: 0.6821. Min Range: -0.6821

Max Act: 0.6821. Min Act: -0.0000

Data Index: 283822 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.6192. Min Act: -0.0000

Data Index: 875104 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1216792 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5222. Min Act: -0.0000

Data Index: 702878 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1303225 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4883. Min Act: -0.0000

Data Index: 860058 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1054590 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1247339 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4611. Min Act: -0.0001

Data Index: 747641 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1331377 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4384. Min Act: -0.0000

Data Index: 200986 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4550. Min Act: -0.0000

Data Index: 747709 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4650. Min Act: -0.0000

Data Index: 382203 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4660. Min Act: -0.0000

Data Index: 395723 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1013130 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4236. Min Act: -0.0000

Data Index: 657491 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1130030 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4371. Min Act: -0.0000

Data Index: 810902 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1116610 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4138. Min Act: -0.0000

Data Index: 545845 (C4 (Web Text))

Max Activating Token Index: 222