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

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

Neuron 5798 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: 6.7110. Min Range: -6.7110

Max Act: 6.7110. Min Act: -0.0000

Data Index: 410540 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.9892. Min Act: -0.0000

Data Index: 562485 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.7651. Min Act: -0.0000

Data Index: 919386 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.5725. Min Act: -0.0000

Data Index: 154073 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.9703. Min Act: -0.0000

Data Index: 338620 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.7588. Min Act: -0.0000

Data Index: 360680 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.5282. Min Act: -0.0000

Data Index: 395590 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.3008. Min Act: -0.0000

Data Index: 21024 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.1990. Min Act: -0.0000

Data Index: 925352 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 6.7110. Min Range: -6.7110

Max Act: 5.0544. Min Act: -0.0000

Data Index: 1177960 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.6993. Min Act: -0.0000

Data Index: 1078986 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.9236. Min Act: -0.0000

Data Index: 636791 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.5064. Min Act: -0.0000

Data Index: 86553 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.6310. Min Act: -0.0000

Data Index: 310580 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.4688. Min Act: -0.0000

Data Index: 1022133 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.7072. Min Act: -0.0000

Data Index: 1290337 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.4763. Min Act: -0.0000

Data Index: 413580 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.6361. Min Act: -0.0000

Data Index: 1189932 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 6.7110. Min Range: -6.7110

Max Act: 4.4127. Min Act: -0.0000

Data Index: 1072300 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 6.7110. Min Range: -6.7110

Max Act: 3.8592. Min Act: -0.0000

Data Index: 470745 (C4 (Web Text))

Max Activating Token Index: 205