Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0515. Min Act: -0.0005

Data Index: 1014874 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0497. Min Act: -0.0005

Data Index: 138696 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0503. Min Act: -0.0005

Data Index: 540400 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0497. Min Act: -0.0005

Data Index: 1066459 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0457. Min Act: -0.0005

Data Index: 1343181 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0438. Min Act: -0.0005

Data Index: 1022191 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0463. Min Act: -0.0005

Data Index: 619784 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0441. Min Act: -0.0005

Data Index: 1164113 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0441. Min Act: -0.0005

Data Index: 849611 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0438. Min Act: -0.0005

Data Index: 783833 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0435. Min Act: -0.0005

Data Index: 909934 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0426. Min Act: -0.0005

Data Index: 216091 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0424. Min Act: -0.0005

Data Index: 434908 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0430. Min Act: -0.0005

Data Index: 311427 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0423. Min Act: -0.0005

Data Index: 870263 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0412. Min Act: -0.0005

Data Index: 1655 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0421. Min Act: -0.0005

Data Index: 774543 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0431. Min Act: -0.0005

Data Index: 46915 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0432. Min Act: -0.0005

Data Index: 984071 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0413. Min Act: -0.0005

Data Index: 264604 (C4 (Web Text))

Max Activating Token Index: 891