Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3010 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2812. Min Act: -0.0001

Data Index: 809399 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2396. Min Act: -0.0001

Data Index: 900999 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2404. Min Act: -0.0001

Data Index: 246282 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2293. Min Act: -0.0000

Data Index: 559116 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2213. Min Act: -0.0001

Data Index: 78975 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2135. Min Act: -0.0001

Data Index: 380448 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1270880 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1918. Min Act: -0.0001

Data Index: 953506 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1919. Min Act: -0.0001

Data Index: 970990 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2076. Min Act: -0.0001

Data Index: 854410 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1906. Min Act: -0.0001

Data Index: 725318 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1879. Min Act: -0.0001

Data Index: 191623 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1202095 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1960. Min Act: -0.0001

Data Index: 957454 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1161393 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2000. Min Act: -0.0001

Data Index: 243893 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1156233 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1843. Min Act: -0.0001

Data Index: 896256 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1901. Min Act: -0.0001

Data Index: 20049 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1755. Min Act: -0.0001

Data Index: 209939 (C4 (Web Text))

Max Activating Token Index: 280