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

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

Neuron 683 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0901. Min Act: -0.0002

Data Index: 538078 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0146. Min Act: -0.0001

Data Index: 1358511 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0406. Min Act: -0.0002

Data Index: 783391 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0646. Min Act: -0.0002

Data Index: 376642 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0051. Min Act: -0.0001

Data Index: 719779 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0225. Min Act: -0.0001

Data Index: 208460 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9915. Min Act: -0.0002

Data Index: 297241 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9808. Min Act: -0.0001

Data Index: 151792 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9579. Min Act: -0.0002

Data Index: 386196 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9001. Min Act: -0.0002

Data Index: 591626 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8652. Min Act: -0.0001

Data Index: 408618 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9766. Min Act: -0.0002

Data Index: 740769 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9548. Min Act: -0.0002

Data Index: 1049407 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9810. Min Act: -0.0001

Data Index: 328622 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0646. Min Act: -0.0001

Data Index: 709881 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9966. Min Act: -0.0002

Data Index: 1206832 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9090. Min Act: -0.0002

Data Index: 585564 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9372. Min Act: -0.0001

Data Index: 442199 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9287. Min Act: -0.0001

Data Index: 815857 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9039. Min Act: -0.0002

Data Index: 111167 (C4 (Web Text))

Max Activating Token Index: 108