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

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

Neuron 1809 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0002

Data Index: 566840 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1310481 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0471. Min Act: -0.0002

Data Index: 517013 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0445. Min Act: -0.0002

Data Index: 930825 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0448. Min Act: -0.0001

Data Index: 718500 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0463. Min Act: -0.0002

Data Index: 984511 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0441. Min Act: -0.0002

Data Index: 109101 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1300768 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1151035 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0441. Min Act: -0.0002

Data Index: 254667 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0419. Min Act: -0.0002

Data Index: 350854 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1311395 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1083135 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0404. Min Act: -0.0002

Data Index: 722633 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0417. Min Act: -0.0002

Data Index: 302361 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1068973 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1247355 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0428. Min Act: -0.0002

Data Index: 615375 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0426. Min Act: -0.0002

Data Index: 415647 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0416. Min Act: -0.0002

Data Index: 453728 (C4 (Web Text))

Max Activating Token Index: 768