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

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

Neuron 1778 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: 0.0626. Min Range: -0.0626

Max Act: 0.0626. Min Act: -0.0003

Data Index: 160311 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0457. Min Act: -0.0003

Data Index: 14636 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1220797 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0451. Min Act: -0.0003

Data Index: 539921 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1049661 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0438. Min Act: -0.0003

Data Index: 962650 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1222503 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0433. Min Act: -0.0003

Data Index: 346900 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0427. Min Act: -0.0003

Data Index: 297105 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0434. Min Act: -0.0003

Data Index: 387810 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1234787 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0421. Min Act: -0.0003

Data Index: 672581 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0412. Min Act: -0.0003

Data Index: 59206 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1210358 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1328422 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0416. Min Act: -0.0003

Data Index: 801024 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1054454 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0411. Min Act: -0.0003

Data Index: 348324 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0409. Min Act: -0.0004

Data Index: 285342 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0404. Min Act: -0.0004

Data Index: 425240 (C4 (Web Text))

Max Activating Token Index: 607