Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.5172. Min Act: -0.0000

Data Index: 830821 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.4693. Min Act: -0.0001

Data Index: 588916 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1088527 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1269801 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.4093. Min Act: -0.0000

Data Index: 737537 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1222010 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.4037. Min Act: -0.0000

Data Index: 320578 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.4125. Min Act: -0.0000

Data Index: 222606 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3890. Min Act: -0.0000

Data Index: 779967 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3858. Min Act: -0.0000

Data Index: 252813 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3782. Min Act: -0.0001

Data Index: 696958 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3649. Min Act: -0.0000

Data Index: 809319 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1087489 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3698. Min Act: -0.0000

Data Index: 256962 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3403. Min Act: -0.0001

Data Index: 903208 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3622. Min Act: -0.0001

Data Index: 229737 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3623. Min Act: -0.0000

Data Index: 154969 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1031577 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3614. Min Act: -0.0000

Data Index: 885201 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.5172. Min Range: -0.5172

Max Act: 0.3479. Min Act: -0.0000

Data Index: 907398 (C4 (Web Text))

Max Activating Token Index: 362