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

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

Neuron 280 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2333. Min Act: -0.0000

Data Index: 988737 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2336. Min Act: -0.0001

Data Index: 315143 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2163. Min Act: -0.0001

Data Index: 588725 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2145. Min Act: -0.0000

Data Index: 901536 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2187. Min Act: -0.0001

Data Index: 510847 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1077344 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1933. Min Act: -0.0000

Data Index: 766525 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1996. Min Act: -0.0000

Data Index: 942490 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1968. Min Act: -0.0000

Data Index: 925499 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1874. Min Act: -0.0001

Data Index: 192949 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1802. Min Act: -0.0000

Data Index: 189230 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1925. Min Act: -0.0001

Data Index: 865118 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1931. Min Act: -0.0000

Data Index: 129177 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1356228 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1848. Min Act: -0.0001

Data Index: 708010 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1859. Min Act: -0.0001

Data Index: 930799 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1008577 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1918. Min Act: -0.0000

Data Index: 807471 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1783. Min Act: -0.0000

Data Index: 887492 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1913. Min Act: -0.0000

Data Index: 351604 (C4 (Web Text))

Max Activating Token Index: 991