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

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

Neuron 18 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.2561. Min Act: -0.0000

Data Index: 681349 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1052390 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.3635. Min Act: -0.0000

Data Index: 606634 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1358852 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.9578. Min Act: -0.0000

Data Index: 811540 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.0044. Min Act: -0.0000

Data Index: 900370 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.0379. Min Act: -0.0001

Data Index: 19830 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1054826 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.9527. Min Act: -0.0000

Data Index: 131655 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1207105 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.9807. Min Act: -0.0000

Data Index: 912007 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1092400 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8849. Min Act: -0.0000

Data Index: 471817 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1318320 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1351261 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8597. Min Act: -0.0000

Data Index: 433428 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1168014 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7651. Min Act: -0.0000

Data Index: 624646 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7419. Min Act: -0.0000

Data Index: 90531 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1114800 (C4 (Web Text))

Max Activating Token Index: 318