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

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

Neuron 1993 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1145539 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1092. Min Act: -0.0001

Data Index: 229331 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0979. Min Act: -0.0001

Data Index: 269139 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0998. Min Act: -0.0001

Data Index: 531412 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0944. Min Act: -0.0001

Data Index: 228364 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1102234 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0900. Min Act: -0.0001

Data Index: 12487 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0957. Min Act: -0.0001

Data Index: 857005 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0854. Min Act: -0.0001

Data Index: 938281 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1137168 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0886. Min Act: -0.0001

Data Index: 409772 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0882. Min Act: -0.0001

Data Index: 561046 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0835. Min Act: -0.0001

Data Index: 552243 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1352373 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1318227 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0849. Min Act: -0.0001

Data Index: 362122 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1319603 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0843. Min Act: -0.0001

Data Index: 451485 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0841. Min Act: -0.0001

Data Index: 680847 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1346654 (C4 (Web Text))

Max Activating Token Index: 487