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

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

Neuron 1762 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: 0.2665. Min Range: -0.2665

Max Act: 0.2665. Min Act: -0.0001

Data Index: 942807 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2340. Min Act: -0.0001

Data Index: 879874 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2419. Min Act: -0.0001

Data Index: 169540 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2205. Min Act: -0.0001

Data Index: 643379 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1125461 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2031. Min Act: -0.0001

Data Index: 596368 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2001. Min Act: -0.0001

Data Index: 297847 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2007. Min Act: -0.0001

Data Index: 1338005 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2120. Min Act: -0.0001

Data Index: 260627 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2018. Min Act: -0.0001

Data Index: 486572 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1999. Min Act: -0.0001

Data Index: 55637 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1202008 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1979. Min Act: -0.0001

Data Index: 684924 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1900. Min Act: -0.0001

Data Index: 389629 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1104433 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2019. Min Act: -0.0001

Data Index: 869772 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1118475 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1949. Min Act: -0.0001

Data Index: 666554 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1810. Min Act: -0.0001

Data Index: 301799 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1911. Min Act: -0.0001

Data Index: 12106 (C4 (Web Text))

Max Activating Token Index: 139