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

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

Neuron 648 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4920. Min Act: -0.0000

Data Index: 400492 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4751. Min Act: -0.0000

Data Index: 910482 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1090074 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1170391 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4049. Min Act: -0.0000

Data Index: 99917 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4086. Min Act: -0.0000

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1258641 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3689. Min Act: -0.0000

Data Index: 530587 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3498. Min Act: -0.0000

Data Index: 569692 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3206. Min Act: -0.0000

Data Index: 662087 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1648058 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2994. Min Act: -0.0000

Data Index: 908178 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3100. Min Act: -0.0000

Data Index: 283628 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1188708 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1152703 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2992. Min Act: -0.0000

Data Index: 626294 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1640108 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2607. Min Act: -0.0000

Data Index: 565962 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1126361 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1483128 (Python Code)

Max Activating Token Index: 915