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

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

Neuron 3035 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2306. Min Range: -3.2306

Max Act: 3.2306. Min Act: -0.0000

Data Index: 213550 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1218013 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.6482. Min Act: -0.0000

Data Index: 1241198 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.5997. Min Act: -0.0000

Data Index: 722083 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.4546. Min Act: -0.0000

Data Index: 54975 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.5055. Min Act: -0.0000

Data Index: 315232 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.5071. Min Act: -0.0000

Data Index: 916874 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.2236. Min Act: -0.0000

Data Index: 148478 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.2792. Min Act: -0.0000

Data Index: 383703 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.2504. Min Act: -0.0000

Data Index: 705106 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.2427. Min Act: -0.0000

Data Index: 1010826 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.1933. Min Act: -0.0000

Data Index: 353193 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.3419. Min Act: -0.0000

Data Index: 354768 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.1417. Min Act: -0.0000

Data Index: 490752 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 3.2306. Min Range: -3.2306

Max Act: 1.9984. Min Act: -0.0000

Data Index: 1192682 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.0678. Min Act: -0.0000

Data Index: 1217857 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.2306. Min Range: -3.2306

Max Act: 1.9579. Min Act: 0.0000

Data Index: 388611 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 3.2306. Min Range: -3.2306

Max Act: 1.8453. Min Act: -0.0000

Data Index: 1209610 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 3.2306. Min Range: -3.2306

Max Act: 2.1752. Min Act: 0.0000

Data Index: 821729 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 3.2306. Min Range: -3.2306

Max Act: 1.8784. Min Act: -0.0000

Data Index: 508635 (C4 (Web Text))

Max Activating Token Index: 495