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

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

Neuron 5287 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0838. Min Range: -2.0838

Max Act: 2.0838. Min Act: -0.0000

Data Index: 1342643 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1077491 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.9016. Min Act: -0.0000

Data Index: 327319 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.7895. Min Act: -0.0000

Data Index: 51109 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.6786. Min Act: -0.0000

Data Index: 851616 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.9574. Min Act: -0.0000

Data Index: 392615 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.7706. Min Act: -0.0000

Data Index: 1353606 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.6908. Min Act: -0.0000

Data Index: 1291380 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.7431. Min Act: -0.0000

Data Index: 869684 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.6203. Min Act: -0.0000

Data Index: 556347 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.6867. Min Act: -0.0000

Data Index: 634743 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.5776. Min Act: -0.0000

Data Index: 222865 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1059804 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.5420. Min Act: -0.0000

Data Index: 1331487 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.6306. Min Act: -0.0000

Data Index: 1157185 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.6255. Min Act: -0.0000

Data Index: 485452 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.6184. Min Act: -0.0000

Data Index: 844002 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1190301 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.5816. Min Act: -0.0000

Data Index: 894019 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 2.0838. Min Range: -2.0838

Max Act: 1.5792. Min Act: -0.0000

Data Index: 793045 (C4 (Web Text))

Max Activating Token Index: 205