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

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

Neuron 4226 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: 4.0815. Min Range: -4.0815

Max Act: 3.7798. Min Act: -0.0000

Data Index: 657783 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.8968. Min Act: -0.0000

Data Index: 178467 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 4.0815. Min Range: -4.0815

Max Act: 4.0815. Min Act: -0.0001

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.8414. Min Act: -0.0000

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.4240. Min Act: -0.0001

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.5027. Min Act: -0.0000

Data Index: 1358570 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.4281. Min Act: -0.0000

Data Index: 666882 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.3949. Min Act: -0.0000

Data Index: 628184 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.2044. Min Act: -0.0001

Data Index: 1047793 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.4940. Min Act: -0.0000

Data Index: 1278995 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.1693. Min Act: -0.0000

Data Index: 684129 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.1364. Min Act: -0.0000

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.2954. Min Act: -0.0001

Data Index: 461706 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.2715. Min Act: -0.0000

Data Index: 809993 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.1446. Min Act: -0.0000

Data Index: 1064172 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.1278. Min Act: -0.0000

Data Index: 929830 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.3594. Min Act: -0.0001

Data Index: 1347504 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.0781. Min Act: -0.0000

Data Index: 421907 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.0518. Min Act: -0.0000

Data Index: 700621 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 4.0815. Min Range: -4.0815

Max Act: 3.0455. Min Act: -0.0000

Data Index: 602864 (C4 (Web Text))

Max Activating Token Index: 181