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

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

Neuron 2070 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.7399. Min Act: -0.0000

Data Index: 1111531 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.4304. Min Act: -0.0000

Data Index: 858140 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2858. Min Act: -0.0000

Data Index: 134974 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2743. Min Act: -0.0000

Data Index: 397661 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.4362. Min Act: -0.0000

Data Index: 485834 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2614. Min Act: -0.0000

Data Index: 493146 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.5087. Min Act: -0.0000

Data Index: 3787 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.3553. Min Act: -0.0000

Data Index: 11242 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.1958. Min Act: -0.0000

Data Index: 936725 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.4380. Min Act: -0.0000

Data Index: 130776 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2894. Min Act: -0.0000

Data Index: 1241033 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2573. Min Act: -0.0000

Data Index: 312546 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2787. Min Act: -0.0000

Data Index: 203413 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.3477. Min Act: -0.0000

Data Index: 1054962 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2223. Min Act: -0.0000

Data Index: 1229885 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.1899. Min Act: -0.0000

Data Index: 321094 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.0243. Min Act: -0.0000

Data Index: 1014083 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.1054. Min Act: -0.0000

Data Index: 374519 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 3.7399. Min Range: -3.7399

Max Act: 3.2470. Min Act: -0.0000

Data Index: 1256034 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 3.7399. Min Range: -3.7399

Max Act: 2.9385. Min Act: -0.0000

Data Index: 808232 (C4 (Web Text))

Max Activating Token Index: 776