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

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

Neuron 2792 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: 2.0110. Min Range: -2.0110

Max Act: 2.0110. Min Act: -0.0000

Data Index: 607055 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.7056. Min Act: -0.0000

Data Index: 439491 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.8696. Min Act: -0.0000

Data Index: 205753 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.9625. Min Act: -0.0000

Data Index: 943209 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.7245. Min Act: -0.0000

Data Index: 331847 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.6898. Min Act: -0.0000

Data Index: 818218 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.8283. Min Act: -0.0001

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.6028. Min Act: -0.0001

Data Index: 303700 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.4649. Min Act: -0.0001

Data Index: 403052 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.4693. Min Act: -0.0001

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.3503. Min Act: -0.0001

Data Index: 1264212 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.3544. Min Act: -0.0001

Data Index: 1226042 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.2864. Min Act: -0.0000

Data Index: 170464 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.3526. Min Act: -0.0001

Data Index: 317652 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.3808. Min Act: -0.0000

Data Index: 199879 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.3480. Min Act: -0.0001

Data Index: 452135 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.3757. Min Act: -0.0000

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1075921 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.2613. Min Act: -0.0001

Data Index: 146192 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 2.0110. Min Range: -2.0110

Max Act: 1.2605. Min Act: -0.0001

Data Index: 639932 (C4 (Web Text))

Max Activating Token Index: 467