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

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

Neuron 1351 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: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0003

Data Index: 572360 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1008048 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0463. Min Act: -0.0002

Data Index: 660862 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0450. Min Act: -0.0003

Data Index: 192233 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1154815 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1283092 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0431. Min Act: -0.0004

Data Index: 547924 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0419. Min Act: -0.0003

Data Index: 746981 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0415. Min Act: 0.0001

Data Index: 360713 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1652629 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0416. Min Act: -0.0004

Data Index: 1267714 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0408. Min Act: -0.0002

Data Index: 676505 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0396. Min Act: -0.0003

Data Index: 711931 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1256065 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0401. Min Act: -0.0004

Data Index: 1124728 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1051471 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1115904 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0400. Min Act: -0.0003

Data Index: 198712 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0406. Min Act: -0.0003

Data Index: 527794 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0390. Min Act: -0.0003

Data Index: 373775 (C4 (Web Text))

Max Activating Token Index: 363