Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1333214 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3219. Min Act: -0.0000

Data Index: 213926 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1191128 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2462. Min Act: -0.0000

Data Index: 601681 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2382. Min Act: -0.0000

Data Index: 360443 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2219. Min Act: -0.0000

Data Index: 490910 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2146. Min Act: -0.0001

Data Index: 382843 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2046. Min Act: -0.0001

Data Index: 715473 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2029. Min Act: -0.0000

Data Index: 415876 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1986. Min Act: -0.0001

Data Index: 827175 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1965. Min Act: -0.0000

Data Index: 946747 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1963. Min Act: -0.0000

Data Index: 974794 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1868. Min Act: -0.0001

Data Index: 955946 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1863. Min Act: -0.0001

Data Index: 990761 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1808. Min Act: -0.0001

Data Index: 648344 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1064481 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1828. Min Act: -0.0001

Data Index: 359989 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1648325 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1573. Min Act: -0.0001

Data Index: 430455 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.1618. Min Act: -0.0000

Data Index: 658603 (C4 (Web Text))

Max Activating Token Index: 290