Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4535 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 905062 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1030737 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0564. Min Act: -0.0002

Data Index: 391188 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0572. Min Act: -0.0002

Data Index: 188898 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1205517 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0511. Min Act: -0.0002

Data Index: 247687 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1301840 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0472. Min Act: -0.0002

Data Index: 315020 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0462. Min Act: -0.0002

Data Index: 78021 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0453. Min Act: -0.0002

Data Index: 54420 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0455. Min Act: -0.0002

Data Index: 625328 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1502164 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1316527 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1116180 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0443. Min Act: -0.0002

Data Index: 355808 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1147040 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1156957 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1284689 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1561178 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0431. Min Act: -0.0002

Data Index: 28416 (C4 (Web Text))

Max Activating Token Index: 39