Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2408 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3262. Min Act: -0.0000

Data Index: 109901 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1221470 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3396. Min Act: -0.0000

Data Index: 626748 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3064. Min Act: -0.0000

Data Index: 468604 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1201951 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2945. Min Act: -0.0000

Data Index: 440610 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3034. Min Act: -0.0000

Data Index: 372700 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3101. Min Act: -0.0000

Data Index: 367292 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3164. Min Act: -0.0000

Data Index: 913730 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2940. Min Act: -0.0000

Data Index: 160749 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2774. Min Act: -0.0000

Data Index: 238301 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2684. Min Act: -0.0000

Data Index: 534539 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2595. Min Act: -0.0000

Data Index: 120524 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2570. Min Act: -0.0000

Data Index: 664211 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1244020 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2517. Min Act: -0.0000

Data Index: 993897 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2525. Min Act: -0.0000

Data Index: 532559 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1199882 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2515. Min Act: -0.0000

Data Index: 770049 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2426. Min Act: -0.0000

Data Index: 665016 (C4 (Web Text))

Max Activating Token Index: 611