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

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

Neuron 2189 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.8436. Min Act: -0.0000

Data Index: 745166 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.8117. Min Act: -0.0001

Data Index: 920254 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.8105. Min Act: -0.0001

Data Index: 347774 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.7012. Min Act: -0.0001

Data Index: 832012 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6917. Min Act: -0.0000

Data Index: 556340 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6713. Min Act: -0.0000

Data Index: 386239 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6873. Min Act: -0.0001

Data Index: 1343340 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.7077. Min Act: -0.0000

Data Index: 663425 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6435. Min Act: -0.0000

Data Index: 63484 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6253. Min Act: -0.0000

Data Index: 864495 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6035. Min Act: -0.0001

Data Index: 751316 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5311. Min Act: -0.0000

Data Index: 858532 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5588. Min Act: -0.0000

Data Index: 642351 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5943. Min Act: -0.0000

Data Index: 997452 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5559. Min Act: -0.0001

Data Index: 192851 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5696. Min Act: -0.0001

Data Index: 635307 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5799. Min Act: -0.0000

Data Index: 684981 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5631. Min Act: -0.0001

Data Index: 703107 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5475. Min Act: -0.0000

Data Index: 950746 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5079. Min Act: -0.0001

Data Index: 637627 (C4 (Web Text))

Max Activating Token Index: 207