Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 973 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5346. Min Act: -0.0000

Data Index: 587732 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5810. Min Act: -0.0000

Data Index: 482493 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1057044 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3977. Min Act: -0.0000

Data Index: 659641 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4289. Min Act: -0.0000

Data Index: 512316 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4045. Min Act: -0.0000

Data Index: 112288 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1078069 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3887. Min Act: -0.0000

Data Index: 653919 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3793. Min Act: -0.0000

Data Index: 643852 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3671. Min Act: -0.0000

Data Index: 557390 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3776. Min Act: -0.0000

Data Index: 943604 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3534. Min Act: 0.0000

Data Index: 1243867 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3538. Min Act: 0.0000

Data Index: 1175683 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3620. Min Act: -0.0000

Data Index: 133962 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1241817 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3605. Min Act: -0.0001

Data Index: 63873 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3448. Min Act: -0.0000

Data Index: 900461 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3447. Min Act: -0.0000

Data Index: 573899 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1355379 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3533. Min Act: -0.0000

Data Index: 34604 (C4 (Web Text))

Max Activating Token Index: 738