Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 306 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0569. Min Act: -0.0003

Data Index: 489336 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0003

Data Index: 28186 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0513. Min Act: -0.0003

Data Index: 367940 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0497. Min Act: -0.0004

Data Index: 184255 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0502. Min Act: -0.0003

Data Index: 6696 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0500. Min Act: -0.0003

Data Index: 663593 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0499. Min Act: -0.0003

Data Index: 469480 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0489. Min Act: -0.0003

Data Index: 732922 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0468. Min Act: -0.0003

Data Index: 341075 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1024670 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0460. Min Act: -0.0003

Data Index: 211258 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0468. Min Act: -0.0004

Data Index: 515786 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1269348 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0457. Min Act: -0.0003

Data Index: 349137 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1290988 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0455. Min Act: -0.0003

Data Index: 888083 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0446. Min Act: -0.0003

Data Index: 933756 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1264520 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0448. Min Act: -0.0003

Data Index: 751374 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1144272 (C4 (Web Text))

Max Activating Token Index: 140