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

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

Neuron 1919 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.1042. Min Act: -0.0001

Data Index: 369241 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.4262. Min Act: -0.0000

Data Index: 211097 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.2074. Min Act: -0.0001

Data Index: 888774 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.1563. Min Act: -0.0001

Data Index: 762204 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0973. Min Act: -0.0001

Data Index: 821779 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0785. Min Act: -0.0001

Data Index: 388426 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0987. Min Act: -0.0001

Data Index: 891922 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0098. Min Act: -0.0001

Data Index: 124381 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0283. Min Act: -0.0001

Data Index: 430510 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0541. Min Act: -0.0001

Data Index: 803621 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.4262. Min Range: -1.4262

Max Act: 0.9907. Min Act: -0.0001

Data Index: 1342065 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0829. Min Act: -0.0001

Data Index: 1281577 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.4262. Min Range: -1.4262

Max Act: 0.8802. Min Act: -0.0001

Data Index: 567638 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0291. Min Act: -0.0001

Data Index: 615390 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 1.4262. Min Range: -1.4262

Max Act: 0.9569. Min Act: -0.0001

Data Index: 29183 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0403. Min Act: -0.0001

Data Index: 1149833 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0044. Min Act: -0.0001

Data Index: 939257 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.4262. Min Range: -1.4262

Max Act: 1.0068. Min Act: -0.0001

Data Index: 591749 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.4262. Min Range: -1.4262

Max Act: 0.9746. Min Act: -0.0001

Data Index: 175536 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.4262. Min Range: -1.4262

Max Act: 0.9633. Min Act: -0.0001

Data Index: 1009473 (C4 (Web Text))

Max Activating Token Index: 218