Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3434 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2843. Min Range: -2.2843

Max Act: 2.2843. Min Act: -0.0000

Data Index: 1139224 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 2.2843. Min Range: -2.2843

Max Act: 2.0405. Min Act: -0.0000

Data Index: 549630 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 2.2843. Min Range: -2.2843

Max Act: 2.2260. Min Act: -0.0000

Data Index: 465685 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.9791. Min Act: -0.0000

Data Index: 1049262 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 2.2843. Min Range: -2.2843

Max Act: 2.0070. Min Act: -0.0000

Data Index: 177748 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.6839. Min Act: -0.0000

Data Index: 664982 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.4935. Min Act: -0.0000

Data Index: 521837 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.5404. Min Act: -0.0000

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.7020. Min Act: -0.0000

Data Index: 229682 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.3958. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.6191. Min Act: -0.0000

Data Index: 83579 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.4354. Min Act: -0.0000

Data Index: 676539 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.4214. Min Act: -0.0000

Data Index: 885476 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.5464. Min Act: -0.0000

Data Index: 507548 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.4782. Min Act: -0.0000

Data Index: 501745 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.4114. Min Act: -0.0000

Data Index: 917705 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.3197. Min Act: -0.0000

Data Index: 554528 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.4536. Min Act: -0.0000

Data Index: 798457 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.4909. Min Act: -0.0000

Data Index: 216599 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 2.2843. Min Range: -2.2843

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1119806 (C4 (Web Text))

Max Activating Token Index: 588