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

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

Neuron 1352 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.4121. Min Act: -0.0000

Data Index: 262755 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3426. Min Act: -0.0001

Data Index: 552133 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3415. Min Act: -0.0000

Data Index: 24844 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3161. Min Act: -0.0000

Data Index: 37596 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3141. Min Act: -0.0000

Data Index: 295499 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3043. Min Act: -0.0000

Data Index: 345605 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2906. Min Act: -0.0001

Data Index: 999171 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2776. Min Act: -0.0000

Data Index: 659580 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2895. Min Act: -0.0001

Data Index: 1236617 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2745. Min Act: -0.0001

Data Index: 994641 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2737. Min Act: -0.0000

Data Index: 587096 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2651. Min Act: -0.0001

Data Index: 747165 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2794. Min Act: -0.0001

Data Index: 465985 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2782. Min Act: -0.0001

Data Index: 591375 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2605. Min Act: -0.0001

Data Index: 122880 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2615. Min Act: -0.0001

Data Index: 416793 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2615. Min Act: -0.0000

Data Index: 632869 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2553. Min Act: -0.0000

Data Index: 124822 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2444. Min Act: -0.0001

Data Index: 1055794 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2518. Min Act: -0.0000

Data Index: 80834 (C4 (Web Text))

Max Activating Token Index: 458