Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5303 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.9845. Min Act: -0.0000

Data Index: 563493 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.8173. Min Act: -0.0000

Data Index: 475525 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.7101. Min Act: -0.0000

Data Index: 611581 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.7784. Min Act: -0.0000

Data Index: 656467 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1334023 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.6571. Min Act: -0.0000

Data Index: 688628 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.5660. Min Act: -0.0000

Data Index: 1105020 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.6389. Min Act: -0.0000

Data Index: 82238 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.6705. Min Act: -0.0000

Data Index: 346077 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4838. Min Act: -0.0000

Data Index: 126154 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.5837. Min Act: -0.0000

Data Index: 84843 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4752. Min Act: -0.0000

Data Index: 319707 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.5406. Min Act: -0.0000

Data Index: 884922 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.6265. Min Act: -0.0000

Data Index: 657799 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.5241. Min Act: -0.0000

Data Index: 799677 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4557. Min Act: -0.0000

Data Index: 476554 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4467. Min Act: -0.0000

Data Index: 303728 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.5053. Min Act: -0.0000

Data Index: 193368 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.6006. Min Act: -0.0000

Data Index: 1161535 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1283222 (C4 (Web Text))

Max Activating Token Index: 339