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

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

Neuron 3245 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1047021 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4475. Min Act: -0.0000

Data Index: 6446 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1146864 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1260509 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.3210. Min Act: -0.0000

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2842. Min Act: -0.0000

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2903. Min Act: -0.0000

Data Index: 986844 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2867. Min Act: -0.0000

Data Index: 599749 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1274133 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2591. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2715. Min Act: -0.0000

Data Index: 504610 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2617. Min Act: -0.0000

Data Index: 129228 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2564. Min Act: -0.0000

Data Index: 163246 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1153715 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2279. Min Act: -0.0000

Data Index: 163814 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1078595 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1327135 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1275155 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.2404. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 620