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

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

Neuron 1072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.8332. Min Act: -0.0000

Data Index: 737378 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.5049. Min Act: -0.0000

Data Index: 44795 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.3340. Min Act: -0.0000

Data Index: 705975 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.2552. Min Act: -0.0000

Data Index: 364228 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1026992 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1257854 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.2021. Min Act: -0.0000

Data Index: 272651 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.1666. Min Act: -0.0000

Data Index: 909001 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.2336. Min Act: -0.0000

Data Index: 88236 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.1443. Min Act: -0.0000

Data Index: 400926 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.2699. Min Act: -0.0000

Data Index: 515083 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.1660. Min Act: -0.0000

Data Index: 665063 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.2449. Min Act: -0.0000

Data Index: 412146 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.1716. Min Act: -0.0000

Data Index: 957380 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1280099 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.1396. Min Act: -0.0000

Data Index: 631254 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.1393. Min Act: -0.0000

Data Index: 514437 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1320612 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.8332. Min Range: -1.8332

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1169966 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.8332. Min Range: -1.8332

Max Act: 1.1080. Min Act: -0.0000

Data Index: 522772 (C4 (Web Text))

Max Activating Token Index: 554