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

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

Neuron 1989 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: 0.0687. Min Range: -0.0687

Max Act: 0.0686. Min Act: -0.0004

Data Index: 1182490 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0002

Data Index: 275431 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0638. Min Act: -0.0003

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0614. Min Act: -0.0003

Data Index: 459572 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1084091 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1071729 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0617. Min Act: -0.0003

Data Index: 411397 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0629. Min Act: -0.0003

Data Index: 879466 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0612. Min Act: -0.0003

Data Index: 345591 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0592. Min Act: -0.0003

Data Index: 124432 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0608. Min Act: -0.0003

Data Index: 661763 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0686. Min Act: -0.0003

Data Index: 729205 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0608. Min Act: -0.0002

Data Index: 508354 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0612. Min Act: -0.0003

Data Index: 973187 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0596. Min Act: -0.0003

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0593. Min Act: -0.0003

Data Index: 298919 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0597. Min Act: -0.0003

Data Index: 479156 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1425881 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0592. Min Act: -0.0003

Data Index: 326552 (C4 (Web Text))

Max Activating Token Index: 163