Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1644 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0006

Data Index: 999250 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1013801 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0421. Min Act: -0.0006

Data Index: 274437 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0425. Min Act: -0.0006

Data Index: 1058831 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0386. Min Act: -0.0006

Data Index: 22370 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0393. Min Act: -0.0006

Data Index: 921064 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0352. Min Act: -0.0006

Data Index: 1264237 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0361. Min Act: -0.0006

Data Index: 59010 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0361. Min Act: -0.0006

Data Index: 888265 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1193460 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1245524 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0380. Min Act: -0.0006

Data Index: 923228 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0384. Min Act: -0.0006

Data Index: 748514 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0381. Min Act: -0.0006

Data Index: 966519 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0356. Min Act: -0.0006

Data Index: 1172712 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0378. Min Act: -0.0006

Data Index: 349767 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1325434 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0367. Min Act: -0.0006

Data Index: 268262 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0365. Min Act: -0.0006

Data Index: 1165905 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0348. Min Act: -0.0006

Data Index: 502492 (C4 (Web Text))

Max Activating Token Index: 658