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

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

Neuron 3298 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: 2.0891. Min Range: -2.0891

Max Act: 2.0891. Min Act: -0.0000

Data Index: 668376 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.8117. Min Act: 0.0000

Data Index: 766508 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1247421 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.5190. Min Act: -0.0000

Data Index: 1161194 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1191952 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.6691. Min Act: -0.0000

Data Index: 1338080 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.6210. Min Act: 0.0000

Data Index: 113481 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1245935 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1002350 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.3566. Min Act: -0.0000

Data Index: 109801 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.3978. Min Act: -0.0000

Data Index: 624838 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1205782 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1138350 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.3720. Min Act: 0.0000

Data Index: 27689 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.4487. Min Act: -0.0000

Data Index: 1092560 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.3595. Min Act: -0.0000

Data Index: 19339 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1014861 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.3424. Min Act: -0.0000

Data Index: 680936 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.2570. Min Act: -0.0000

Data Index: 646795 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 2.0891. Min Range: -2.0891

Max Act: 1.2453. Min Act: -0.0000

Data Index: 523495 (C4 (Web Text))

Max Activating Token Index: 76