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

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

Neuron 3857 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6798. Min Act: -0.0000

Data Index: 479205 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6162. Min Act: -0.0000

Data Index: 204010 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6150. Min Act: -0.0000

Data Index: 679230 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1179685 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1310751 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6071. Min Act: -0.0000

Data Index: 941627 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1173124 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5746. Min Act: -0.0000

Data Index: 573558 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5743. Min Act: -0.0000

Data Index: 794917 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1038426 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5280. Min Act: -0.0000

Data Index: 771166 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5046. Min Act: -0.0000

Data Index: 308760 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1242604 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5620. Min Act: -0.0000

Data Index: 661560 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5352. Min Act: -0.0000

Data Index: 604760 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5440. Min Act: -0.0000

Data Index: 355656 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1193930 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1117409 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5236. Min Act: -0.0000

Data Index: 746211 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5065. Min Act: -0.0000

Data Index: 275295 (C4 (Web Text))

Max Activating Token Index: 25