Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2017 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0003

Data Index: 139243 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0483. Min Act: -0.0003

Data Index: 590964 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0493. Min Act: -0.0003

Data Index: 339621 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0483. Min Act: -0.0003

Data Index: 743284 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1242271 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0458. Min Act: -0.0003

Data Index: 65103 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1297304 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0472. Min Act: -0.0003

Data Index: 825739 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0462. Min Act: -0.0003

Data Index: 421804 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0451. Min Act: -0.0003

Data Index: 278742 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1347904 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0445. Min Act: -0.0003

Data Index: 92265 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0451. Min Act: -0.0002

Data Index: 916668 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0003

Data Index: 937766 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0444. Min Act: -0.0003

Data Index: 248181 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0003

Data Index: 853098 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0003

Data Index: 848658 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1006020 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0448. Min Act: -0.0003

Data Index: 737776 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0437. Min Act: -0.0003

Data Index: 396821 (C4 (Web Text))

Max Activating Token Index: 319