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

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

Neuron 2308 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: 6.6715. Min Range: -6.6715

Max Act: 6.6715. Min Act: -0.0000

Data Index: 118974 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 6.6715. Min Range: -6.6715

Max Act: 5.1436. Min Act: -0.0000

Data Index: 1227707 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 6.6715. Min Range: -6.6715

Max Act: 4.6450. Min Act: -0.0000

Data Index: 218264 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 6.6715. Min Range: -6.6715

Max Act: 4.3038. Min Act: -0.0000

Data Index: 1192902 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 6.6715. Min Range: -6.6715

Max Act: 4.2744. Min Act: -0.0000

Data Index: 704580 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 6.6715. Min Range: -6.6715

Max Act: 4.1695. Min Act: -0.0000

Data Index: 491824 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 6.6715. Min Range: -6.6715

Max Act: 4.1550. Min Act: -0.0000

Data Index: 243125 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 6.6715. Min Range: -6.6715

Max Act: 4.1106. Min Act: -0.0000

Data Index: 1163124 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 6.6715. Min Range: -6.6715

Max Act: 4.0752. Min Act: -0.0000

Data Index: 860599 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.9046. Min Act: -0.0000

Data Index: 1327710 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.8532. Min Act: -0.0000

Data Index: 599971 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.8461. Min Act: -0.0000

Data Index: 1211891 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.8699. Min Act: -0.0000

Data Index: 126414 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.8079. Min Act: -0.0000

Data Index: 1325617 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.8297. Min Act: -0.0000

Data Index: 1298158 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.7448. Min Act: -0.0000

Data Index: 406967 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.4629. Min Act: -0.0000

Data Index: 1311670 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.5546. Min Act: -0.0000

Data Index: 123502 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.3661. Min Act: -0.0000

Data Index: 864407 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 6.6715. Min Range: -6.6715

Max Act: 3.6869. Min Act: -0.0000

Data Index: 248122 (C4 (Web Text))

Max Activating Token Index: 956