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

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

Neuron 4342 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.1880. Min Act: -0.0000

Data Index: 261281 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.1520. Min Act: -0.0000

Data Index: 1010170 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.9887. Min Act: -0.0000

Data Index: 57787 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8873. Min Act: -0.0000

Data Index: 210165 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.0803. Min Act: -0.0000

Data Index: 856199 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.0687. Min Act: -0.0000

Data Index: 415040 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.1674. Min Act: -0.0000

Data Index: 744523 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.0471. Min Act: -0.0000

Data Index: 657819 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.1571. Min Act: -0.0000

Data Index: 751704 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.0225. Min Act: -0.0000

Data Index: 364310 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8695. Min Act: -0.0000

Data Index: 335517 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.0806. Min Act: -0.0000

Data Index: 700019 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.9790. Min Act: -0.0000

Data Index: 1179046 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.9720. Min Act: -0.0000

Data Index: 136460 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.0598. Min Act: -0.0000

Data Index: 1054981 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8468. Min Act: -0.0000

Data Index: 1315699 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.9330. Min Act: -0.0000

Data Index: 1656665 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8998. Min Act: -0.0000

Data Index: 243221 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8833. Min Act: -0.0000

Data Index: 557172 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8845. Min Act: -0.0000

Data Index: 935190 (C4 (Web Text))

Max Activating Token Index: 379