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

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

Neuron 3775 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2708. Min Range: -4.2708

Max Act: 4.2708. Min Act: -0.0000

Data Index: 785306 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 4.2708. Min Range: -4.2708

Max Act: 4.1668. Min Act: -0.0000

Data Index: 1060859 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 4.2708. Min Range: -4.2708

Max Act: 4.1043. Min Act: -0.0000

Data Index: 915473 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 4.2708. Min Range: -4.2708

Max Act: 4.1628. Min Act: -0.0000

Data Index: 532581 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 4.2708. Min Range: -4.2708

Max Act: 4.1349. Min Act: -0.0000

Data Index: 553600 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.8913. Min Act: -0.0000

Data Index: 598875 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.8892. Min Act: -0.0000

Data Index: 1076571 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.9934. Min Act: -0.0000

Data Index: 222595 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.9481. Min Act: -0.0000

Data Index: 865880 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.6523. Min Act: -0.0000

Data Index: 566188 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.6571. Min Act: -0.0000

Data Index: 847925 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.4896. Min Act: -0.0000

Data Index: 828275 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.4940. Min Act: -0.0000

Data Index: 481982 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.6190. Min Act: -0.0000

Data Index: 1105000 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.5518. Min Act: -0.0000

Data Index: 1108411 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.5495. Min Act: -0.0000

Data Index: 234402 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.5563. Min Act: -0.0000

Data Index: 477558 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.7018. Min Act: -0.0000

Data Index: 566008 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.4930. Min Act: -0.0000

Data Index: 241002 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 4.2708. Min Range: -4.2708

Max Act: 3.4952. Min Act: -0.0000

Data Index: 47799 (C4 (Web Text))

Max Activating Token Index: 994