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

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

Neuron 3181 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1067507 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7005. Min Act: -0.0000

Data Index: 879915 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6587. Min Act: -0.0000

Data Index: 398566 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5947. Min Act: -0.0000

Data Index: 708337 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5819. Min Act: -0.0000

Data Index: 585075 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5515. Min Act: -0.0000

Data Index: 690168 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1265665 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1225407 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1132012 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5359. Min Act: -0.0000

Data Index: 190700 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5287. Min Act: -0.0000

Data Index: 578360 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5605. Min Act: -0.0000

Data Index: 425689 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.4873. Min Act: -0.0000

Data Index: 272517 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5219. Min Act: 0.0000

Data Index: 956068 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1231626 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5092. Min Act: -0.0000

Data Index: 769092 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5245. Min Act: -0.0000

Data Index: 684306 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.4907. Min Act: -0.0000

Data Index: 952305 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5011. Min Act: -0.0000

Data Index: 247121 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.4976. Min Act: -0.0000

Data Index: 599734 (C4 (Web Text))

Max Activating Token Index: 896