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

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

Neuron 4470 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1709. Min Range: -7.1709

Max Act: 7.1288. Min Act: -0.0001

Data Index: 1321091 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 7.1709. Min Range: -7.1709

Max Act: 7.1709. Min Act: -0.0001

Data Index: 746114 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 7.1709. Min Range: -7.1709

Max Act: 7.0176. Min Act: -0.0001

Data Index: 446265 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 7.1709. Min Range: -7.1709

Max Act: 6.2698. Min Act: -0.0001

Data Index: 462413 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.8508. Min Act: -0.0001

Data Index: 970878 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.8363. Min Act: -0.0001

Data Index: 110895 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 7.1709. Min Range: -7.1709

Max Act: 6.2857. Min Act: -0.0001

Data Index: 1213176 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 7.1709. Min Range: -7.1709

Max Act: 6.9263. Min Act: -0.0001

Data Index: 535061 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.5751. Min Act: -0.0001

Data Index: 1069766 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.7039. Min Act: -0.0001

Data Index: 1047783 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.5128. Min Act: -0.0001

Data Index: 1009698 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.6616. Min Act: -0.0001

Data Index: 348578 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.6331. Min Act: -0.0001

Data Index: 678277 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 7.1709. Min Range: -7.1709

Max Act: 6.0969. Min Act: -0.0001

Data Index: 729352 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.1277. Min Act: -0.0001

Data Index: 1090874 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 7.1709. Min Range: -7.1709

Max Act: 4.7591. Min Act: -0.0001

Data Index: 1007494 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 7.1709. Min Range: -7.1709

Max Act: 4.1417. Min Act: -0.0001

Data Index: 841625 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 7.1709. Min Range: -7.1709

Max Act: 4.6434. Min Act: -0.0001

Data Index: 1049794 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 7.1709. Min Range: -7.1709

Max Act: 4.8974. Min Act: -0.0001

Data Index: 1164433 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 7.1709. Min Range: -7.1709

Max Act: 5.4098. Min Act: -0.0001

Data Index: 688173 (C4 (Web Text))

Max Activating Token Index: 473