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

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

Neuron 5407 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: 6.0619. Min Range: -6.0619

Max Act: 6.0619. Min Act: -0.0000

Data Index: 297456 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.4674. Min Act: -0.0000

Data Index: 938362 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 6.0619. Min Range: -6.0619

Max Act: 4.8433. Min Act: -0.0000

Data Index: 943506 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.2085. Min Act: -0.0000

Data Index: 700000 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.4858. Min Act: -0.0000

Data Index: 319407 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.3235. Min Act: -0.0000

Data Index: 679724 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.2412. Min Act: -0.0000

Data Index: 717134 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.2219. Min Act: -0.0000

Data Index: 99334 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.0353. Min Act: -0.0000

Data Index: 1329238 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.2405. Min Act: -0.0000

Data Index: 243437 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.0630. Min Act: -0.0000

Data Index: 764545 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.0423. Min Act: -0.0000

Data Index: 580041 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.0281. Min Act: -0.0000

Data Index: 61024 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.3770. Min Act: -0.0000

Data Index: 1036309 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 6.0619. Min Range: -6.0619

Max Act: 4.9808. Min Act: -0.0000

Data Index: 1213969 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.2318. Min Act: -0.0000

Data Index: 1263428 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 6.0619. Min Range: -6.0619

Max Act: 4.9223. Min Act: -0.0000

Data Index: 995859 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.0569. Min Act: -0.0000

Data Index: 412679 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.0589. Min Act: -0.0000

Data Index: 1030736 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 6.0619. Min Range: -6.0619

Max Act: 5.0456. Min Act: -0.0000

Data Index: 1153588 (C4 (Web Text))

Max Activating Token Index: 454