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

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

Neuron 250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1591. Min Range: -2.1591

Max Act: 2.1591. Min Act: -0.0000

Data Index: 165032 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.8569. Min Act: -0.0000

Data Index: 1094073 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.7992. Min Act: -0.0000

Data Index: 730598 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1179547 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.6970. Min Act: -0.0000

Data Index: 34189 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.7952. Min Act: -0.0000

Data Index: 555784 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.5429. Min Act: -0.0000

Data Index: 266548 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.6175. Min Act: -0.0000

Data Index: 747927 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1024413 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1221553 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1034102 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.5910. Min Act: -0.0000

Data Index: 260305 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.5061. Min Act: -0.0000

Data Index: 196728 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.4216. Min Act: -0.0000

Data Index: 915566 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1314016 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1236691 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.2343. Min Act: -0.0000

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1284169 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.3913. Min Act: -0.0000

Data Index: 798659 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 2.1591. Min Range: -2.1591

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1085819 (C4 (Web Text))

Max Activating Token Index: 288