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

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

Neuron 300 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: 3.9513. Min Range: -3.9513

Max Act: 3.9513. Min Act: -0.0000

Data Index: 216118 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.0487. Min Act: -0.0000

Data Index: 399751 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.4460. Min Act: -0.0000

Data Index: 699114 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.8091. Min Act: -0.0000

Data Index: 553409 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.6515. Min Act: -0.0000

Data Index: 850848 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.4801. Min Act: -0.0000

Data Index: 55272 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.4307. Min Act: -0.0000

Data Index: 168367 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.3839. Min Act: -0.0000

Data Index: 199145 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.3305. Min Act: -0.0000

Data Index: 731954 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.3354. Min Act: -0.0000

Data Index: 988042 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.5037. Min Act: -0.0000

Data Index: 414826 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.2391. Min Act: -0.0000

Data Index: 102496 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 3.9513. Min Range: -3.9513

Max Act: 1.9756. Min Act: -0.0000

Data Index: 192902 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.3299. Min Act: -0.0000

Data Index: 1277495 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.2990. Min Act: -0.0000

Data Index: 889553 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.0861. Min Act: -0.0000

Data Index: 241333 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.0241. Min Act: -0.0000

Data Index: 125557 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.1172. Min Act: -0.0000

Data Index: 1333704 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.2310. Min Act: -0.0000

Data Index: 143002 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.1991. Min Act: -0.0000

Data Index: 843938 (C4 (Web Text))

Max Activating Token Index: 403