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

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

Neuron 4844 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: 3.5365. Min Range: -3.5365

Max Act: 3.5365. Min Act: -0.0000

Data Index: 992599 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1685. Min Act: -0.0000

Data Index: 1084191 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.2033. Min Act: -0.0000

Data Index: 825357 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.9911. Min Act: -0.0000

Data Index: 121527 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.0088. Min Act: -0.0000

Data Index: 1059980 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.1752. Min Act: -0.0000

Data Index: 67104 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.0867. Min Act: -0.0000

Data Index: 1033678 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.8780. Min Act: -0.0000

Data Index: 1220303 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.2924. Min Act: -0.0000

Data Index: 1075758 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.0372. Min Act: -0.0000

Data Index: 944847 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.8216. Min Act: -0.0000

Data Index: 1160354 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.7904. Min Act: -0.0000

Data Index: 271317 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.8585. Min Act: -0.0000

Data Index: 1175185 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.5411. Min Act: -0.0000

Data Index: 364539 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.7967. Min Act: -0.0000

Data Index: 625672 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 3.5365. Min Range: -3.5365

Max Act: 3.0418. Min Act: -0.0000

Data Index: 1231348 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1278905 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.4779. Min Act: -0.0000

Data Index: 92251 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.8649. Min Act: -0.0000

Data Index: 349180 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 3.5365. Min Range: -3.5365

Max Act: 2.3636. Min Act: -0.0000

Data Index: 1008645 (C4 (Web Text))

Max Activating Token Index: 380