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

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

Neuron 423 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.7876. Min Act: 0.0000

Data Index: 959503 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.4455. Min Act: -0.0000

Data Index: 448285 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.3707. Min Act: 0.0000

Data Index: 489318 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.4385. Min Act: -0.0000

Data Index: 703342 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.4320. Min Act: -0.0000

Data Index: 1039305 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.3620. Min Act: 0.0001

Data Index: 318265 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.3526. Min Act: -0.0000

Data Index: 330185 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.3034. Min Act: -0.0000

Data Index: 759924 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1253212 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.3774. Min Act: -0.0000

Data Index: 478481 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1019816 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.2202. Min Act: -0.0000

Data Index: 784123 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.2017. Min Act: 0.0000

Data Index: 291010 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.0930. Min Act: -0.0000

Data Index: 338679 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.1515. Min Act: 0.0000

Data Index: 942990 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.1408. Min Act: -0.0000

Data Index: 901225 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.1426. Min Act: -0.0000

Data Index: 760358 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.1433. Min Act: -0.0000

Data Index: 668366 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.1016. Min Act: -0.0000

Data Index: 621864 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.7876. Min Range: -1.7876

Max Act: 1.0979. Min Act: 0.0000

Data Index: 1236343 (C4 (Web Text))

Max Activating Token Index: 825