Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2560 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1230823 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1003986 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1031638 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.6985. Min Act: -0.0000

Data Index: 30201 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.6857. Min Act: -0.0000

Data Index: 716644 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.6848. Min Act: -0.0000

Data Index: 795243 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4855. Min Act: -0.0000

Data Index: 211163 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1341705 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4859. Min Act: -0.0000

Data Index: 114872 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4423. Min Act: -0.0000

Data Index: 404902 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4478. Min Act: -0.0000

Data Index: 799451 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4233. Min Act: -0.0000

Data Index: 195082 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4386. Min Act: -0.0000

Data Index: 574815 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4440. Min Act: -0.0000

Data Index: 727468 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4188. Min Act: -0.0000

Data Index: 380083 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4048. Min Act: -0.0000

Data Index: 952939 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4000. Min Act: -0.0000

Data Index: 11073 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3889. Min Act: -0.0000

Data Index: 92134 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4074. Min Act: -0.0000

Data Index: 770694 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4232. Min Act: -0.0000

Data Index: 44754 (C4 (Web Text))

Max Activating Token Index: 501