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

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

Neuron 611 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0001

Data Index: 260207 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0759. Min Act: -0.0001

Data Index: 550445 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0580. Min Act: -0.0001

Data Index: 443041 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0550. Min Act: -0.0001

Data Index: 947517 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1192812 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0541. Min Act: -0.0001

Data Index: 890520 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0532. Min Act: 0.0000

Data Index: 970878 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0531. Min Act: -0.0001

Data Index: 832567 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0545. Min Act: -0.0001

Data Index: 954450 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0541. Min Act: -0.0001

Data Index: 350189 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0516. Min Act: -0.0000

Data Index: 684738 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0508. Min Act: -0.0001

Data Index: 280265 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0496. Min Act: -0.0001

Data Index: 403120 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0502. Min Act: -0.0001

Data Index: 661698 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0501. Min Act: 0.0000

Data Index: 329811 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1357723 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0489. Min Act: -0.0001

Data Index: 230151 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0548. Min Act: -0.0001

Data Index: 341087 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0485. Min Act: -0.0001

Data Index: 670258 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1006907 (C4 (Web Text))

Max Activating Token Index: 537