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

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

Neuron 2662 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: 0.5158. Min Range: -0.5158

Max Act: 0.5158. Min Act: -0.0001

Data Index: 302617 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4713. Min Act: -0.0001

Data Index: 1326843 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4504. Min Act: -0.0001

Data Index: 1299701 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4280. Min Act: -0.0001

Data Index: 934400 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4335. Min Act: -0.0001

Data Index: 341177 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3747. Min Act: -0.0001

Data Index: 675380 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4190. Min Act: -0.0001

Data Index: 1115546 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3991. Min Act: -0.0001

Data Index: 175750 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3863. Min Act: -0.0001

Data Index: 1343874 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4460. Min Act: -0.0001

Data Index: 1034673 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4053. Min Act: -0.0001

Data Index: 876913 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3700. Min Act: -0.0001

Data Index: 603011 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3997. Min Act: -0.0001

Data Index: 539765 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3745. Min Act: -0.0001

Data Index: 458500 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3743. Min Act: -0.0001

Data Index: 882521 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3443. Min Act: -0.0001

Data Index: 1299079 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3706. Min Act: -0.0001

Data Index: 739630 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3683. Min Act: -0.0001

Data Index: 811387 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3868. Min Act: -0.0001

Data Index: 967541 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3379. Min Act: -0.0001

Data Index: 531350 (C4 (Web Text))

Max Activating Token Index: 86