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

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

Neuron 3774 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: 0.3607. Min Range: -0.3607

Max Act: 0.3607. Min Act: -0.0000

Data Index: 593970 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2920. Min Act: -0.0000

Data Index: 541711 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1202692 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2846. Min Act: -0.0001

Data Index: 222393 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2900. Min Act: -0.0000

Data Index: 97541 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2980. Min Act: -0.0000

Data Index: 171160 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2882. Min Act: -0.0001

Data Index: 1338146 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2959. Min Act: -0.0000

Data Index: 235032 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1304334 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2772. Min Act: -0.0000

Data Index: 155770 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2752. Min Act: -0.0001

Data Index: 49007 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2541. Min Act: -0.0001

Data Index: 1304660 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1037102 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2693. Min Act: -0.0001

Data Index: 1207179 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2602. Min Act: -0.0000

Data Index: 886320 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2687. Min Act: -0.0000

Data Index: 869166 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2578. Min Act: -0.0001

Data Index: 537601 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2585. Min Act: -0.0000

Data Index: 621540 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2548. Min Act: -0.0000

Data Index: 484858 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2540. Min Act: -0.0001

Data Index: 52771 (C4 (Web Text))

Max Activating Token Index: 333