Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1006 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3153. Min Act: -0.0002

Data Index: 567532 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2726. Min Act: -0.0002

Data Index: 1406910 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2649. Min Act: -0.0002

Data Index: 1583540 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2985. Min Act: -0.0002

Data Index: 1608065 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3065. Min Act: -0.0002

Data Index: 1524590 (Python Code)

Max Activating Token Index: 812

Text #5

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2697. Min Act: -0.0002

Data Index: 1482389 (Python Code)

Max Activating Token Index: 450

Text #6

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2820. Min Act: -0.0002

Data Index: 1388315 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2691. Min Act: -0.0002

Data Index: 1552713 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2775. Min Act: -0.0002

Data Index: 395617 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1558630 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2677. Min Act: -0.0002

Data Index: 1631937 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2720. Min Act: -0.0002

Data Index: 1422404 (Python Code)

Max Activating Token Index: 711

Text #12

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2710. Min Act: -0.0002

Data Index: 183067 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2580. Min Act: -0.0002

Data Index: 240505 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2650. Min Act: -0.0002

Data Index: 1406277 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2700. Min Act: -0.0002

Data Index: 1584304 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2405. Min Act: -0.0002

Data Index: 872881 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2708. Min Act: -0.0002

Data Index: 408714 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2556. Min Act: -0.0002

Data Index: 1525538 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2700. Min Act: -0.0003

Data Index: 1503872 (Python Code)

Max Activating Token Index: 159