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

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

Neuron 2931 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.3281. Min Act: -0.0001

Data Index: 1578971 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1474142 (Python Code)

Max Activating Token Index: 820

Text #2

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1415411 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.3093. Min Act: -0.0001

Data Index: 265070 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1572423 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1410672 (Python Code)

Max Activating Token Index: 530

Text #6

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2817. Min Act: -0.0001

Data Index: 955206 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2760. Min Act: -0.0001

Data Index: 1650350 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2731. Min Act: -0.0001

Data Index: 1455364 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1486654 (Python Code)

Max Activating Token Index: 535

Text #10

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1280859 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2603. Min Act: -0.0001

Data Index: 420409 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2543. Min Act: -0.0001

Data Index: 876104 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2559. Min Act: -0.0001

Data Index: 970171 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1582007 (Python Code)

Max Activating Token Index: 782

Text #15

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1418610 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2551. Min Act: -0.0001

Data Index: 373907 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2414. Min Act: -0.0001

Data Index: 663804 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2180. Min Act: -0.0001

Data Index: 835037 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.3281. Min Range: -0.3281

Max Act: 0.2413. Min Act: -0.0001

Data Index: 822006 (C4 (Web Text))

Max Activating Token Index: 779