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

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

Neuron 410 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.4664. Min Act: -0.0001

Data Index: 1252239 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0559. Min Act: -0.0000

Data Index: 457419 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.1047. Min Act: -0.0001

Data Index: 1273035 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0970. Min Act: -0.0001

Data Index: 401888 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0843. Min Act: -0.0001

Data Index: 542409 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0349. Min Act: -0.0000

Data Index: 585439 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0679. Min Act: -0.0001

Data Index: 455604 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9736. Min Act: -0.0000

Data Index: 364937 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1081265 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9960. Min Act: -0.0000

Data Index: 172630 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9126. Min Act: -0.0000

Data Index: 114727 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9447. Min Act: -0.0000

Data Index: 563926 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1032197 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0054. Min Act: -0.0001

Data Index: 1251640 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9230. Min Act: -0.0000

Data Index: 296636 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.8838. Min Act: -0.0000

Data Index: 915190 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1264215 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.8592. Min Act: -0.0000

Data Index: 131617 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9087. Min Act: -0.0000

Data Index: 451268 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.8749. Min Act: -0.0000

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 423