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

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

Neuron 4514 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: 4.4488. Min Range: -4.4488

Max Act: 4.4488. Min Act: -0.0000

Data Index: 912188 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.6679. Min Act: -0.0000

Data Index: 1206427 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.4923. Min Act: -0.0000

Data Index: 605181 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.6247. Min Act: -0.0000

Data Index: 956020 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.4533. Min Act: -0.0000

Data Index: 1080102 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.7593. Min Act: -0.0000

Data Index: 1014088 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.4634. Min Act: -0.0000

Data Index: 420188 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.1599. Min Act: -0.0000

Data Index: 967369 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.4238. Min Act: -0.0000

Data Index: 682454 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.4184. Min Act: -0.0000

Data Index: 956107 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.4108. Min Act: -0.0000

Data Index: 893637 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.5148. Min Act: -0.0000

Data Index: 838483 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.2522. Min Act: -0.0000

Data Index: 955182 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.2522. Min Act: -0.0000

Data Index: 1331452 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.1637. Min Act: -0.0000

Data Index: 103677 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 4.4488. Min Range: -4.4488

Max Act: 2.9981. Min Act: -0.0000

Data Index: 690075 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.1172. Min Act: -0.0000

Data Index: 102102 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 4.4488. Min Range: -4.4488

Max Act: 2.9915. Min Act: -0.0000

Data Index: 298235 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.0693. Min Act: -0.0000

Data Index: 928368 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 4.4488. Min Range: -4.4488

Max Act: 3.0439. Min Act: -0.0000

Data Index: 207009 (C4 (Web Text))

Max Activating Token Index: 714