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

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

Neuron 4191 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3802. Min Act: -0.0000

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3759. Min Act: -0.0000

Data Index: 145374 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3525. Min Act: -0.0000

Data Index: 428188 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3362. Min Act: -0.0000

Data Index: 656528 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3084. Min Act: -0.0000

Data Index: 700016 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1169714 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1235758 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2748. Min Act: -0.0000

Data Index: 26443 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1330055 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2679. Min Act: -0.0000

Data Index: 57370 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1298257 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1212109 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2690. Min Act: -0.0000

Data Index: 764344 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2618. Min Act: -0.0000

Data Index: 303201 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1038266 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1295454 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2519. Min Act: -0.0000

Data Index: 212797 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2503. Min Act: -0.0000

Data Index: 546999 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1358090 (C4 (Web Text))

Max Activating Token Index: 367