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

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

Neuron 911 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.0474. Min Range: -1.0474

Max Act: 1.0474. Min Act: -0.0002

Data Index: 545808 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.0474. Min Range: -1.0474

Max Act: 1.0406. Min Act: -0.0002

Data Index: 926052 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.0474. Min Range: -1.0474

Max Act: 1.0264. Min Act: -0.0002

Data Index: 1320256 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.0474. Min Range: -1.0474

Max Act: 1.0145. Min Act: -0.0002

Data Index: 843182 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9824. Min Act: -0.0003

Data Index: 939848 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9772. Min Act: -0.0002

Data Index: 1279541 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9988. Min Act: -0.0002

Data Index: 1196315 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9662. Min Act: -0.0002

Data Index: 1309419 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9778. Min Act: -0.0002

Data Index: 317866 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9777. Min Act: -0.0003

Data Index: 862181 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9627. Min Act: -0.0002

Data Index: 815356 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9543. Min Act: -0.0002

Data Index: 1083950 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9666. Min Act: -0.0002

Data Index: 1229137 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9901. Min Act: -0.0002

Data Index: 358592 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9686. Min Act: -0.0002

Data Index: 348 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9672. Min Act: -0.0002

Data Index: 769254 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9498. Min Act: -0.0002

Data Index: 294964 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9353. Min Act: -0.0002

Data Index: 1115056 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9303. Min Act: -0.0002

Data Index: 760615 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9254. Min Act: -0.0002

Data Index: 605079 (C4 (Web Text))

Max Activating Token Index: 414