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

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

Neuron 101 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2096. Min Range: -3.2096

Max Act: 3.2096. Min Act: -0.0001

Data Index: 1400637 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 3.2096. Min Range: -3.2096

Max Act: 2.7586. Min Act: -0.0000

Data Index: 883746 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 3.2096. Min Range: -3.2096

Max Act: 2.2082. Min Act: -0.0000

Data Index: 119893 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 3.2096. Min Range: -3.2096

Max Act: 2.0679. Min Act: -0.0000

Data Index: 1408821 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 3.2096. Min Range: -3.2096

Max Act: 2.0417. Min Act: -0.0001

Data Index: 586586 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.7893. Min Act: -0.0001

Data Index: 1606664 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.8646. Min Act: -0.0001

Data Index: 1365797 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.5132. Min Act: -0.0001

Data Index: 1567877 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.7874. Min Act: -0.0000

Data Index: 1610511 (Python Code)

Max Activating Token Index: 431

Text #9

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.6336. Min Act: -0.0001

Data Index: 92329 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1634218 (Python Code)

Max Activating Token Index: 229

Text #11

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.6567. Min Act: -0.0000

Data Index: 837569 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.4960. Min Act: -0.0001

Data Index: 561695 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.5663. Min Act: -0.0001

Data Index: 1264151 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1578278 (Python Code)

Max Activating Token Index: 544

Text #15

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.4989. Min Act: -0.0000

Data Index: 792822 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.4090. Min Act: -0.0001

Data Index: 1424836 (Python Code)

Max Activating Token Index: 527

Text #17

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1189575 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1491819 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 3.2096. Min Range: -3.2096

Max Act: 1.5504. Min Act: -0.0001

Data Index: 1371005 (Python Code)

Max Activating Token Index: 542