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

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

Neuron 3591 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: 2.2646. Min Range: -2.2646

Max Act: 2.2646. Min Act: -0.0000

Data Index: 851124 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 2.2646. Min Range: -2.2646

Max Act: 2.2010. Min Act: -0.0000

Data Index: 621708 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 2.2646. Min Range: -2.2646

Max Act: 2.0762. Min Act: -0.0000

Data Index: 817925 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.7060. Min Act: -0.0000

Data Index: 146791 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.7144. Min Act: -0.0000

Data Index: 343061 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.7318. Min Act: -0.0000

Data Index: 466373 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.6141. Min Act: -0.0000

Data Index: 601459 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.8003. Min Act: -0.0001

Data Index: 490047 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1057684 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.6403. Min Act: -0.0000

Data Index: 1237290 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.6463. Min Act: -0.0001

Data Index: 1014512 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.7273. Min Act: -0.0001

Data Index: 645088 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.6263. Min Act: -0.0000

Data Index: 441138 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.6346. Min Act: -0.0000

Data Index: 692752 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.7185. Min Act: -0.0000

Data Index: 771134 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.4959. Min Act: -0.0000

Data Index: 619969 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.6046. Min Act: -0.0000

Data Index: 1224227 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.2659. Min Act: -0.0000

Data Index: 281730 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.6792. Min Act: -0.0000

Data Index: 213618 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 2.2646. Min Range: -2.2646

Max Act: 1.4202. Min Act: -0.0000

Data Index: 694530 (C4 (Web Text))

Max Activating Token Index: 839