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

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

Neuron 5107 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: 0.5438. Min Range: -0.5438

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1221006 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5106. Min Act: -0.0000

Data Index: 448046 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1058356 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4871. Min Act: -0.0000

Data Index: 527417 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4923. Min Act: -0.0000

Data Index: 749474 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1273835 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5247. Min Act: -0.0000

Data Index: 142452 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4900. Min Act: -0.0000

Data Index: 832112 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5111. Min Act: -0.0000

Data Index: 361212 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4203. Min Act: -0.0000

Data Index: 383563 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1322167 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4855. Min Act: -0.0000

Data Index: 900973 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1073686 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4471. Min Act: -0.0000

Data Index: 197682 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4690. Min Act: -0.0000

Data Index: 82247 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1178145 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4404. Min Act: -0.0000

Data Index: 328317 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4371. Min Act: -0.0000

Data Index: 991393 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4469. Min Act: -0.0000

Data Index: 869599 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4565. Min Act: -0.0000

Data Index: 575721 (C4 (Web Text))

Max Activating Token Index: 849