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

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

Neuron 3982 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: -0.0000

Data Index: 200396 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1103. Min Act: -0.0000

Data Index: 233868 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1196100 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1146029 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1020. Min Act: -0.0000

Data Index: 680180 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1062109 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0911. Min Act: -0.0000

Data Index: 153888 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1334779 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0874. Min Act: -0.0000

Data Index: 858683 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0881. Min Act: -0.0000

Data Index: 764114 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0881. Min Act: -0.0000

Data Index: 725187 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1331663 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0821. Min Act: -0.0000

Data Index: 925371 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1253706 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0802. Min Act: -0.0000

Data Index: 264013 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0851. Min Act: -0.0000

Data Index: 301627 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0815. Min Act: -0.0000

Data Index: 354102 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1311350 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0812. Min Act: -0.0000

Data Index: 639350 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1190483 (C4 (Web Text))

Max Activating Token Index: 598