Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4271 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3797. Min Range: -2.3797

Max Act: 2.3797. Min Act: -0.0000

Data Index: 705412 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.3797. Min Range: -2.3797

Max Act: 2.3274. Min Act: -0.0001

Data Index: 924433 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 2.3797. Min Range: -2.3797

Max Act: 2.1855. Min Act: -0.0000

Data Index: 689685 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.8472. Min Act: -0.0000

Data Index: 1302536 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.7897. Min Act: -0.0000

Data Index: 230701 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.7138. Min Act: -0.0000

Data Index: 715434 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.7857. Min Act: -0.0000

Data Index: 384641 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.6446. Min Act: -0.0000

Data Index: 938179 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.5628. Min Act: -0.0000

Data Index: 1125147 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.7379. Min Act: -0.0000

Data Index: 174431 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1034284 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.6531. Min Act: -0.0000

Data Index: 540828 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1180502 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.6251. Min Act: -0.0000

Data Index: 93725 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.7024. Min Act: -0.0000

Data Index: 252059 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.6214. Min Act: -0.0000

Data Index: 1113494 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.5826. Min Act: -0.0000

Data Index: 359241 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.3410. Min Act: -0.0000

Data Index: 231961 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.6104. Min Act: -0.0000

Data Index: 912028 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 2.3797. Min Range: -2.3797

Max Act: 1.5281. Min Act: -0.0000

Data Index: 991333 (C4 (Web Text))

Max Activating Token Index: 532