Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3481 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0001

Data Index: 8806 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1319588 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0459. Min Act: -0.0001

Data Index: 567372 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0498. Min Act: -0.0001

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0386. Min Act: -0.0001

Data Index: 707739 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0501. Min Act: -0.0001

Data Index: 533156 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1282280 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0509. Min Act: -0.0001

Data Index: 864292 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0526. Min Act: -0.0001

Data Index: 496039 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0469. Min Act: -0.0001

Data Index: 995156 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0428. Min Act: -0.0001

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1194629 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0417. Min Act: -0.0001

Data Index: 333881 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0422. Min Act: -0.0001

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0414. Min Act: -0.0001

Data Index: 240801 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0399. Min Act: -0.0001

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0386. Min Act: -0.0001

Data Index: 17185 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0385. Min Act: -0.0001

Data Index: 242477 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1095142 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0382. Min Act: -0.0001

Data Index: 881252 (C4 (Web Text))

Max Activating Token Index: 20