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

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

Neuron 5095 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: 0.6738. Min Range: -0.6738

Max Act: 0.6738. Min Act: -0.0002

Data Index: 1249906 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6039. Min Act: -0.0002

Data Index: 23097 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6277. Min Act: -0.0002

Data Index: 188606 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6416. Min Act: -0.0002

Data Index: 279377 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5372. Min Act: -0.0002

Data Index: 740269 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5701. Min Act: -0.0002

Data Index: 974506 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5450. Min Act: -0.0002

Data Index: 739771 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5646. Min Act: -0.0002

Data Index: 932943 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5413. Min Act: -0.0002

Data Index: 84295 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5025. Min Act: -0.0002

Data Index: 781614 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5015. Min Act: -0.0002

Data Index: 2464 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4922. Min Act: -0.0002

Data Index: 143666 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4773. Min Act: -0.0002

Data Index: 682274 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4687. Min Act: -0.0002

Data Index: 737444 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4441. Min Act: -0.0002

Data Index: 800416 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4396. Min Act: -0.0002

Data Index: 1354020 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4706. Min Act: -0.0002

Data Index: 1127737 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4361. Min Act: -0.0002

Data Index: 921433 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4319. Min Act: -0.0002

Data Index: 308746 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4416. Min Act: -0.0002

Data Index: 825714 (C4 (Web Text))

Max Activating Token Index: 482