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

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

Neuron 3707 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6090. Min Act: -0.0000

Data Index: 849725 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1513850 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1624109 (Python Code)

Max Activating Token Index: 1016

Text #3

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1445635 (Python Code)

Max Activating Token Index: 896

Text #4

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1583908 (Python Code)

Max Activating Token Index: 949

Text #5

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1508666 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5748. Min Act: -0.0000

Data Index: 877756 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1456179 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1459094 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5830. Min Act: -0.0000

Data Index: 65383 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1456065 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1400076 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1510959 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1580172 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1403451 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1379655 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1609010 (Python Code)

Max Activating Token Index: 912

Text #17

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1577665 (Python Code)

Max Activating Token Index: 1001

Text #18

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1368991 (Python Code)

Max Activating Token Index: 802

Text #19

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1623950 (Python Code)

Max Activating Token Index: 727