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

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

Neuron 2112 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: 5.3316. Min Range: -5.3316

Max Act: 5.3316. Min Act: -0.0000

Data Index: 1139258 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 5.3316. Min Range: -5.3316

Max Act: 4.9259. Min Act: -0.0000

Data Index: 667206 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 5.3316. Min Range: -5.3316

Max Act: 4.1132. Min Act: -0.0000

Data Index: 335194 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 5.3316. Min Range: -5.3316

Max Act: 4.4357. Min Act: -0.0000

Data Index: 944742 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 5.3316. Min Range: -5.3316

Max Act: 4.1663. Min Act: -0.0000

Data Index: 583749 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.8183. Min Act: -0.0000

Data Index: 378073 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.7756. Min Act: -0.0000

Data Index: 1238247 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.7370. Min Act: -0.0000

Data Index: 144230 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.8654. Min Act: -0.0000

Data Index: 553019 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.8140. Min Act: -0.0000

Data Index: 390599 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.8081. Min Act: -0.0000

Data Index: 866558 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.5830. Min Act: -0.0000

Data Index: 1154725 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.4095. Min Act: -0.0000

Data Index: 482822 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.5658. Min Act: -0.0000

Data Index: 690346 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.7017. Min Act: -0.0000

Data Index: 605332 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.5361. Min Act: -0.0000

Data Index: 1044087 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.8456. Min Act: -0.0000

Data Index: 459311 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.6856. Min Act: -0.0000

Data Index: 1270936 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.5022. Min Act: -0.0000

Data Index: 874637 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 5.3316. Min Range: -5.3316

Max Act: 3.4218. Min Act: -0.0000

Data Index: 972618 (C4 (Web Text))

Max Activating Token Index: 324