Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 506 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.8848. Min Act: -0.0000

Data Index: 864280 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7691. Min Act: -0.0000

Data Index: 760648 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6460. Min Act: -0.0000

Data Index: 690618 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1206531 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6206. Min Act: -0.0000

Data Index: 883500 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6209. Min Act: -0.0000

Data Index: 940971 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5888. Min Act: -0.0000

Data Index: 173148 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6033. Min Act: -0.0000

Data Index: 409822 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1329529 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1053365 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5656. Min Act: -0.0000

Data Index: 155040 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1216162 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1019953 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5419. Min Act: -0.0000

Data Index: 186732 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1331156 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5347. Min Act: -0.0000

Data Index: 836199 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5592. Min Act: 0.0000

Data Index: 976305 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5400. Min Act: -0.0000

Data Index: 814661 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1128956 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5329. Min Act: -0.0000

Data Index: 993132 (C4 (Web Text))

Max Activating Token Index: 354