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

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

Neuron 5652 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: 2.2966. Min Range: -2.2966

Max Act: 2.1457. Min Act: -0.0000

Data Index: 557898 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.2966. Min Act: -0.0000

Data Index: 587269 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.1523. Min Act: -0.0000

Data Index: 1106549 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.1216. Min Act: -0.0000

Data Index: 569350 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.0802. Min Act: -0.0000

Data Index: 899374 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.1934. Min Act: -0.0000

Data Index: 299343 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.0525. Min Act: -0.0000

Data Index: 1242374 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.1821. Min Act: -0.0000

Data Index: 1249663 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.2813. Min Act: -0.0000

Data Index: 21079 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.1316. Min Act: -0.0000

Data Index: 787014 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.1438. Min Act: -0.0000

Data Index: 87437 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.1332. Min Act: -0.0000

Data Index: 837124 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.2666. Min Act: -0.0000

Data Index: 282699 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.2323. Min Act: -0.0000

Data Index: 611206 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.0277. Min Act: -0.0000

Data Index: 1249329 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 2.2966. Min Range: -2.2966

Max Act: 1.9946. Min Act: -0.0000

Data Index: 10733 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.0824. Min Act: -0.0000

Data Index: 169894 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.0530. Min Act: -0.0000

Data Index: 485308 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 2.2966. Min Range: -2.2966

Max Act: 2.0557. Min Act: -0.0000

Data Index: 68559 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 2.2966. Min Range: -2.2966

Max Act: 1.9512. Min Act: -0.0000

Data Index: 130353 (C4 (Web Text))

Max Activating Token Index: 168