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

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

Neuron 1180 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: 0.2929. Min Range: -0.2929

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1309884 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2481. Min Act: -0.0000

Data Index: 79759 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2684. Min Act: -0.0000

Data Index: 138035 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1152091 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2591. Min Act: -0.0000

Data Index: 520594 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2679. Min Act: -0.0000

Data Index: 892460 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2634. Min Act: -0.0000

Data Index: 794564 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1113133 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1190922 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2391. Min Act: -0.0000

Data Index: 394034 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1311417 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1011588 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2293. Min Act: -0.0000

Data Index: 780922 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2187. Min Act: -0.0000

Data Index: 113924 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2290. Min Act: -0.0000

Data Index: 607469 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1328959 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1044232 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2323. Min Act: -0.0000

Data Index: 48082 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1354144 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2175. Min Act: -0.0000

Data Index: 105544 (C4 (Web Text))

Max Activating Token Index: 936