Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 222 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1200563 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0488. Min Act: -0.0001

Data Index: 740159 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0427. Min Act: -0.0001

Data Index: 639724 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1214261 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0442. Min Act: -0.0001

Data Index: 873614 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0445. Min Act: -0.0001

Data Index: 750330 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0439. Min Act: -0.0001

Data Index: 956990 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1303430 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0417. Min Act: -0.0001

Data Index: 229079 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0408. Min Act: -0.0001

Data Index: 251593 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0381. Min Act: -0.0001

Data Index: 168016 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1022031 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0391. Min Act: -0.0001

Data Index: 348378 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0409. Min Act: -0.0001

Data Index: 547791 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0388. Min Act: -0.0001

Data Index: 418479 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0353. Min Act: -0.0001

Data Index: 486633 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0393. Min Act: -0.0001

Data Index: 157522 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1220982 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0374. Min Act: -0.0001

Data Index: 402169 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1285557 (C4 (Web Text))

Max Activating Token Index: 168