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

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

Neuron 2889 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1308405 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3116. Min Act: -0.0001

Data Index: 1175173 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3055. Min Act: -0.0001

Data Index: 1339226 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1189035 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3028. Min Act: -0.0001

Data Index: 135230 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1344718 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1270010 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2832. Min Act: -0.0000

Data Index: 848331 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2642. Min Act: -0.0000

Data Index: 897206 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1014952 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2617. Min Act: -0.0001

Data Index: 282806 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2603. Min Act: -0.0000

Data Index: 297335 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2571. Min Act: -0.0000

Data Index: 936844 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2625. Min Act: -0.0000

Data Index: 221894 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1043370 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2225. Min Act: -0.0000

Data Index: 609870 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2403. Min Act: -0.0001

Data Index: 153076 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1330359 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2371. Min Act: -0.0000

Data Index: 53832 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2442. Min Act: -0.0001

Data Index: 1302040 (C4 (Web Text))

Max Activating Token Index: 266