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

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

Neuron 1213 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.5058. Min Act: -0.0001

Data Index: 1153414 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4293. Min Act: -0.0001

Data Index: 598163 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4660. Min Act: -0.0001

Data Index: 1007630 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4262. Min Act: -0.0001

Data Index: 680596 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4379. Min Act: -0.0001

Data Index: 1183866 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3803. Min Act: -0.0001

Data Index: 403605 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4163. Min Act: -0.0001

Data Index: 659412 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4245. Min Act: -0.0001

Data Index: 1053054 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3984. Min Act: -0.0001

Data Index: 587309 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4312. Min Act: -0.0001

Data Index: 98424 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3643. Min Act: -0.0001

Data Index: 469229 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3859. Min Act: -0.0001

Data Index: 126408 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1042414 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3479. Min Act: -0.0001

Data Index: 77801 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4060. Min Act: -0.0001

Data Index: 581400 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3892. Min Act: -0.0001

Data Index: 846067 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3399. Min Act: -0.0001

Data Index: 978822 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3981. Min Act: -0.0001

Data Index: 88430 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3983. Min Act: -0.0001

Data Index: 1085316 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3827. Min Act: -0.0001

Data Index: 538611 (C4 (Web Text))

Max Activating Token Index: 19