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

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

Neuron 3649 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: 0.4527. Min Range: -0.4527

Max Act: 0.4527. Min Act: -0.0000

Data Index: 157658 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2202. Min Act: -0.0000

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2249. Min Act: -0.0000

Data Index: 645370 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2164. Min Act: -0.0000

Data Index: 843413 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2003. Min Act: -0.0000

Data Index: 191221 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2189. Min Act: -0.0000

Data Index: 83498 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2147. Min Act: -0.0000

Data Index: 144171 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1552289 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2117. Min Act: -0.0000

Data Index: 816327 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1190460 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2029. Min Act: -0.0000

Data Index: 496718 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2025. Min Act: -0.0000

Data Index: 342753 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2027. Min Act: -0.0000

Data Index: 50223 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.1887. Min Act: -0.0000

Data Index: 132269 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2088. Min Act: -0.0000

Data Index: 408092 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2012. Min Act: -0.0000

Data Index: 364276 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2061. Min Act: -0.0000

Data Index: 314650 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2054. Min Act: -0.0000

Data Index: 747437 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.1806. Min Act: -0.0000

Data Index: 251372 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1575388 (Python Code)

Max Activating Token Index: 70