Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 482 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.4000. Min Act: -0.0000

Data Index: 404193 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1014692 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1706998 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1401615 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1477446 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1000678 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1193949 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2875. Min Act: 0.0000

Data Index: 242066 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2932. Min Act: -0.0000

Data Index: 875664 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2923. Min Act: -0.0000

Data Index: 687830 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2708. Min Act: -0.0000

Data Index: 134372 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2745. Min Act: -0.0000

Data Index: 593231 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2702. Min Act: -0.0000

Data Index: 833577 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2812. Min Act: 0.0001

Data Index: 337082 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2619. Min Act: 0.0001

Data Index: 258228 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2496. Min Act: 0.0001

Data Index: 721192 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1229509 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2470. Min Act: -0.0000

Data Index: 206114 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2372. Min Act: 0.0001

Data Index: 801762 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1342452 (The Pile)

Max Activating Token Index: 313