Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1744 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4849. Min Range: -4.4849

Max Act: 4.4849. Min Act: -0.0001

Data Index: 816030 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 4.4849. Min Range: -4.4849

Max Act: 4.0015. Min Act: -0.0001

Data Index: 49019 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.9570. Min Act: -0.0001

Data Index: 1007404 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.8364. Min Act: -0.0000

Data Index: 39648 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.6621. Min Act: -0.0001

Data Index: 814317 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.7565. Min Act: -0.0001

Data Index: 809375 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.5756. Min Act: -0.0001

Data Index: 1337158 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.5609. Min Act: -0.0000

Data Index: 256950 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.8311. Min Act: -0.0001

Data Index: 981353 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.5848. Min Act: -0.0000

Data Index: 1074332 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.7400. Min Act: -0.0000

Data Index: 225794 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.5385. Min Act: -0.0001

Data Index: 938498 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.2844. Min Act: -0.0001

Data Index: 578849 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.4312. Min Act: -0.0001

Data Index: 1315124 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.4106. Min Act: -0.0001

Data Index: 203748 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.4145. Min Act: -0.0001

Data Index: 1069877 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.3854. Min Act: -0.0001

Data Index: 459161 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.1027. Min Act: -0.0001

Data Index: 183506 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.4435. Min Act: -0.0001

Data Index: 806466 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 4.4849. Min Range: -4.4849

Max Act: 3.1606. Min Act: -0.0001

Data Index: 712151 (C4 (Web Text))

Max Activating Token Index: 637