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

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

Neuron 3373 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5114. Min Range: -4.5114

Max Act: 4.5114. Min Act: -0.0000

Data Index: 330428 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 4.5114. Min Range: -4.5114

Max Act: 4.1898. Min Act: -0.0000

Data Index: 972885 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 4.5114. Min Range: -4.5114

Max Act: 4.0170. Min Act: -0.0000

Data Index: 932925 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 4.5114. Min Range: -4.5114

Max Act: 3.1959. Min Act: -0.0000

Data Index: 156331 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.9133. Min Act: -0.0001

Data Index: 1154480 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.6142. Min Act: -0.0000

Data Index: 1282114 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.6870. Min Act: -0.0001

Data Index: 635637 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.5715. Min Act: -0.0000

Data Index: 950681 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.5041. Min Act: -0.0000

Data Index: 1280043 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.4932. Min Act: -0.0000

Data Index: 841516 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.3665. Min Act: -0.0000

Data Index: 842809 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.5189. Min Act: -0.0000

Data Index: 1312484 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.4211. Min Act: -0.0000

Data Index: 711030 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.3568. Min Act: -0.0000

Data Index: 620201 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.2307. Min Act: -0.0000

Data Index: 651317 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.3092. Min Act: -0.0000

Data Index: 120474 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.1573. Min Act: -0.0000

Data Index: 907759 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.2784. Min Act: -0.0001

Data Index: 687744 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.1437. Min Act: -0.0000

Data Index: 450762 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 4.5114. Min Range: -4.5114

Max Act: 2.1006. Min Act: -0.0000

Data Index: 1326800 (C4 (Web Text))

Max Activating Token Index: 620