Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4290 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.4504. Min Act: -0.0000

Data Index: 115020 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3809. Min Act: -0.0000

Data Index: 780914 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.4043. Min Act: -0.0000

Data Index: 140452 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.4007. Min Act: -0.0000

Data Index: 887307 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3105. Min Act: -0.0000

Data Index: 397018 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1241405 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3089. Min Act: -0.0000

Data Index: 781536 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2820. Min Act: -0.0000

Data Index: 972444 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1197392 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2576. Min Act: -0.0000

Data Index: 585404 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2355. Min Act: -0.0000

Data Index: 240140 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2551. Min Act: -0.0000

Data Index: 477103 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1161287 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2304. Min Act: -0.0000

Data Index: 550892 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2385. Min Act: -0.0000

Data Index: 957902 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2314. Min Act: -0.0000

Data Index: 645046 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2433. Min Act: -0.0000

Data Index: 136602 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2239. Min Act: -0.0000

Data Index: 936358 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1111398 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2146. Min Act: -0.0000

Data Index: 295430 (C4 (Web Text))

Max Activating Token Index: 36