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

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

Neuron 722 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.6220. Min Act: -0.0000

Data Index: 1072074 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.5071. Min Act: -0.0000

Data Index: 692258 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2702. Min Act: -0.0000

Data Index: 968252 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.3605. Min Act: -0.0000

Data Index: 754229 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.5055. Min Act: -0.0000

Data Index: 725172 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.3420. Min Act: -0.0000

Data Index: 1155841 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.4795. Min Act: -0.0000

Data Index: 775743 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.1994. Min Act: -0.0000

Data Index: 1051868 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2633. Min Act: -0.0000

Data Index: 432504 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2661. Min Act: -0.0000

Data Index: 347830 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.1191. Min Act: -0.0000

Data Index: 1073792 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.3733. Min Act: -0.0000

Data Index: 827580 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2273. Min Act: -0.0000

Data Index: 473775 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2164. Min Act: -0.0000

Data Index: 325278 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2926. Min Act: -0.0000

Data Index: 1155342 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.1547. Min Act: -0.0000

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2499. Min Act: -0.0000

Data Index: 629511 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 2.6220. Min Range: -2.6220

Max Act: 1.9969. Min Act: -0.0000

Data Index: 81981 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.2126. Min Act: -0.0000

Data Index: 545621 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 2.6220. Min Range: -2.6220

Max Act: 2.0985. Min Act: -0.0000

Data Index: 1022930 (C4 (Web Text))

Max Activating Token Index: 60