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

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

Neuron 4903 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: 0.0607. Min Range: -0.0607

Max Act: 0.0585. Min Act: -0.0002

Data Index: 722566 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0002

Data Index: 644460 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0538. Min Act: -0.0002

Data Index: 659541 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0500. Min Act: -0.0002

Data Index: 764435 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0509. Min Act: -0.0002

Data Index: 603125 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0501. Min Act: -0.0002

Data Index: 629736 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0468. Min Act: -0.0002

Data Index: 148312 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0472. Min Act: -0.0002

Data Index: 435584 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0437. Min Act: -0.0002

Data Index: 887689 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1202528 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0434. Min Act: -0.0002

Data Index: 815083 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1104161 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0439. Min Act: -0.0002

Data Index: 881977 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0418. Min Act: -0.0002

Data Index: 695483 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1185217 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1276820 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0430. Min Act: -0.0002

Data Index: 324608 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0424. Min Act: -0.0002

Data Index: 53630 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0424. Min Act: -0.0002

Data Index: 855851 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1202946 (C4 (Web Text))

Max Activating Token Index: 664