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

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

Neuron 4031 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1765. Min Range: -3.1765

Max Act: 3.1765. Min Act: -0.0000

Data Index: 277928 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1058443 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.9685. Min Act: -0.0000

Data Index: 1000142 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.0590. Min Act: -0.0000

Data Index: 813015 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.9238. Min Act: -0.0000

Data Index: 1004890 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.9944. Min Act: -0.0000

Data Index: 835249 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.9606. Min Act: -0.0000

Data Index: 417258 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.9087. Min Act: -0.0000

Data Index: 588652 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.7101. Min Act: -0.0000

Data Index: 720982 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.7790. Min Act: -0.0000

Data Index: 834358 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.7521. Min Act: -0.0000

Data Index: 400639 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.7600. Min Act: -0.0000

Data Index: 315560 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.7270. Min Act: -0.0000

Data Index: 811325 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.8044. Min Act: -0.0000

Data Index: 346783 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.6781. Min Act: -0.0000

Data Index: 367602 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.7678. Min Act: -0.0000

Data Index: 166670 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.6734. Min Act: -0.0000

Data Index: 135625 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.6594. Min Act: -0.0000

Data Index: 204869 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.6349. Min Act: -0.0000

Data Index: 1120281 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.1765. Min Range: -3.1765

Max Act: 1.6085. Min Act: -0.0000

Data Index: 631696 (C4 (Web Text))

Max Activating Token Index: 901