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

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

Neuron 3600 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: 0.9784. Min Range: -0.9784

Max Act: 0.9771. Min Act: -0.0000

Data Index: 925980 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1112183 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.8763. Min Act: -0.0000

Data Index: 490981 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1128205 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7355. Min Act: -0.0000

Data Index: 264205 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7203. Min Act: -0.0000

Data Index: 874615 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1032907 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6882. Min Act: 0.0000

Data Index: 1191155 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1170969 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6953. Min Act: 0.0000

Data Index: 414146 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1320064 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7070. Min Act: 0.0000

Data Index: 299984 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1297202 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6733. Min Act: -0.0000

Data Index: 969601 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6749. Min Act: -0.0000

Data Index: 652947 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1350942 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6508. Min Act: -0.0000

Data Index: 319083 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6634. Min Act: 0.0000

Data Index: 375194 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1348852 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1339359 (C4 (Web Text))

Max Activating Token Index: 388