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

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

Neuron 4394 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6329. Min Act: -0.0000

Data Index: 89810 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6314. Min Act: -0.0000

Data Index: 517298 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5891. Min Act: -0.0000

Data Index: 846008 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6055. Min Act: -0.0000

Data Index: 316379 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5779. Min Act: -0.0000

Data Index: 140319 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1116243 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5400. Min Act: -0.0000

Data Index: 496872 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1243278 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5109. Min Act: -0.0000

Data Index: 75572 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1055459 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1232601 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5005. Min Act: -0.0000

Data Index: 881742 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5114. Min Act: -0.0000

Data Index: 217513 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5280. Min Act: -0.0000

Data Index: 379252 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5093. Min Act: -0.0000

Data Index: 663165 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4694. Min Act: -0.0000

Data Index: 627832 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4850. Min Act: -0.0000

Data Index: 305603 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1084826 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4964. Min Act: -0.0000

Data Index: 646404 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4777. Min Act: -0.0000

Data Index: 909631 (C4 (Web Text))

Max Activating Token Index: 123