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

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

Neuron 4522 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0473. Min Act: -0.0002

Data Index: 685056 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0404. Min Act: -0.0002

Data Index: 876085 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1196892 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0434. Min Act: -0.0002

Data Index: 349834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1098655 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1081602 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0497. Min Act: -0.0002

Data Index: 122119 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1324490 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0376. Min Act: -0.0002

Data Index: 544023 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1316809 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1024768 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0375. Min Act: -0.0002

Data Index: 147301 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1225135 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1107991 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1027887 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0365. Min Act: -0.0002

Data Index: 89018 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1092315 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0327. Min Act: -0.0002

Data Index: 677840 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1061828 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0243. Min Act: -0.0002

Data Index: 965161 (C4 (Web Text))

Max Activating Token Index: 742