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

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

Neuron 3412 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: 1.4034. Min Range: -1.4034

Max Act: 1.4034. Min Act: -0.0000

Data Index: 690701 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.2727. Min Act: -0.0000

Data Index: 931526 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0800. Min Act: -0.0000

Data Index: 877125 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9899. Min Act: -0.0000

Data Index: 628007 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0158. Min Act: -0.0000

Data Index: 164437 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9461. Min Act: -0.0000

Data Index: 550862 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9957. Min Act: -0.0000

Data Index: 60786 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8715. Min Act: -0.0000

Data Index: 692613 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9681. Min Act: -0.0000

Data Index: 909887 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0337. Min Act: -0.0000

Data Index: 26208 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9610. Min Act: -0.0000

Data Index: 776503 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9632. Min Act: -0.0000

Data Index: 597764 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9378. Min Act: -0.0000

Data Index: 773820 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1065625 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9274. Min Act: -0.0000

Data Index: 311298 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8334. Min Act: -0.0000

Data Index: 413688 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1190024 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8556. Min Act: -0.0000

Data Index: 50479 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9126. Min Act: -0.0000

Data Index: 107115 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1289649 (C4 (Web Text))

Max Activating Token Index: 366