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

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

Neuron 697 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1273. Min Range: -3.1273

Max Act: 3.1273. Min Act: -0.0001

Data Index: 663625 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.9362. Min Act: -0.0001

Data Index: 169999 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 3.1273. Min Range: -3.1273

Max Act: 3.0751. Min Act: -0.0001

Data Index: 849544 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.9974. Min Act: -0.0000

Data Index: 103081 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.9786. Min Act: -0.0000

Data Index: 1024203 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7990. Min Act: -0.0001

Data Index: 1016709 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.8997. Min Act: -0.0001

Data Index: 1239201 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7558. Min Act: -0.0000

Data Index: 204210 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7395. Min Act: -0.0000

Data Index: 662013 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.8782. Min Act: -0.0000

Data Index: 39602 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.8486. Min Act: -0.0000

Data Index: 728863 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.8485. Min Act: -0.0001

Data Index: 1299065 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.9806. Min Act: -0.0001

Data Index: 722273 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6910. Min Act: -0.0000

Data Index: 415845 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6877. Min Act: -0.0001

Data Index: 290001 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.8290. Min Act: -0.0001

Data Index: 834366 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6591. Min Act: -0.0001

Data Index: 958116 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.5255. Min Act: -0.0000

Data Index: 725666 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6304. Min Act: -0.0001

Data Index: 329905 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7406. Min Act: -0.0000

Data Index: 200871 (C4 (Web Text))

Max Activating Token Index: 284