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

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

Neuron 882 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0636. Min Act: -0.0000

Data Index: 302597 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0655. Min Act: -0.0000

Data Index: 340310 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.7370. Min Act: -0.0000

Data Index: 710527 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0257. Min Act: -0.0000

Data Index: 1204315 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.6023. Min Act: -0.0000

Data Index: 417202 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.3869. Min Act: -0.0000

Data Index: 698798 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.2528. Min Act: -0.0000

Data Index: 1330488 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.3097. Min Act: -0.0000

Data Index: 979864 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.4432. Min Act: -0.0000

Data Index: 473680 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.3236. Min Act: -0.0000

Data Index: 495511 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.1866. Min Act: -0.0000

Data Index: 230232 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.2850. Min Act: -0.0000

Data Index: 606954 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.2712. Min Act: -0.0000

Data Index: 1042362 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.2533. Min Act: -0.0000

Data Index: 1192130 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.1164. Min Act: -0.0000

Data Index: 1317292 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.0744. Min Act: -0.0000

Data Index: 158301 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.1878. Min Act: -0.0000

Data Index: 645075 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.1868. Min Act: -0.0000

Data Index: 911050 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.1739. Min Act: -0.0000

Data Index: 936100 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.1610. Min Act: -0.0000

Data Index: 418923 (C4 (Web Text))

Max Activating Token Index: 679