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

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

Neuron 5627 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: 8.3904. Min Range: -8.3904

Max Act: 8.3904. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 8.3904. Min Range: -8.3904

Max Act: 8.1713. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 8.3904. Min Range: -8.3904

Max Act: 7.8092. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 8.3904. Min Range: -8.3904

Max Act: 6.9004. Min Act: -0.0000

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.6835. Min Act: -0.0000

Data Index: 1099568 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.4224. Min Act: -0.0000

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.0847. Min Act: -0.0000

Data Index: 993928 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.2056. Min Act: -0.0000

Data Index: 1123012 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.1353. Min Act: -0.0000

Data Index: 215822 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.2700. Min Act: -0.0000

Data Index: 453926 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.0507. Min Act: -0.0000

Data Index: 320102 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 8.3904. Min Range: -8.3904

Max Act: 5.0505. Min Act: -0.0000

Data Index: 1420220 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.9913. Min Act: -0.0000

Data Index: 842110 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.9587. Min Act: -0.0000

Data Index: 1028110 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.5365. Min Act: -0.0000

Data Index: 1086399 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.8579. Min Act: -0.0000

Data Index: 612722 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.8205. Min Act: -0.0000

Data Index: 370442 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.7605. Min Act: -0.0000

Data Index: 1647959 (Python Code)

Max Activating Token Index: 661

Text #18

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.7315. Min Act: -0.0000

Data Index: 76635 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 8.3904. Min Range: -8.3904

Max Act: 4.7020. Min Act: -0.0000

Data Index: 1030946 (C4 (Web Text))

Max Activating Token Index: 898