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

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

Neuron 1552 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.7090. Min Act: -0.0000

Data Index: 24704 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.4740. Min Act: -0.0000

Data Index: 1054337 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1352173 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1142618 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1186714 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.3177. Min Act: -0.0000

Data Index: 6438 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.3939. Min Act: -0.0000

Data Index: 329115 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.2107. Min Act: -0.0000

Data Index: 664758 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.2703. Min Act: -0.0000

Data Index: 208033 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.1836. Min Act: -0.0000

Data Index: 926122 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1142457 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1312430 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.2076. Min Act: -0.0000

Data Index: 1197497 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.1912. Min Act: -0.0000

Data Index: 374806 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.1551. Min Act: -0.0000

Data Index: 236095 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1152265 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.2135. Min Act: -0.0000

Data Index: 96486 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.2148. Min Act: -0.0000

Data Index: 24660 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.1335. Min Act: -0.0000

Data Index: 476723 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 1.7090. Min Range: -1.7090

Max Act: 1.1180. Min Act: -0.0000

Data Index: 164947 (C4 (Web Text))

Max Activating Token Index: 979