Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1673. Min Act: -0.0001

Data Index: 164152 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1633. Min Act: -0.0000

Data Index: 647331 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1624. Min Act: -0.0000

Data Index: 131085 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1557. Min Act: -0.0000

Data Index: 644069 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1660. Min Act: -0.0001

Data Index: 119417 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1613. Min Act: -0.0000

Data Index: 776804 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1175237 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1536. Min Act: -0.0001

Data Index: 676640 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1210365 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1484. Min Act: -0.0001

Data Index: 552574 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1530. Min Act: -0.0001

Data Index: 107018 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1513. Min Act: -0.0001

Data Index: 304471 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1248171 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1234133 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1456. Min Act: -0.0000

Data Index: 904313 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1078268 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1285615 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1477. Min Act: -0.0001

Data Index: 621302 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1466. Min Act: -0.0000

Data Index: 570979 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1408. Min Act: -0.0001

Data Index: 836895 (C4 (Web Text))

Max Activating Token Index: 679