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

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

Neuron 2826 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: 3.0538. Min Range: -3.0538

Max Act: 2.6287. Min Act: -0.0000

Data Index: 1007752 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 3.0538. Min Range: -3.0538

Max Act: 3.0538. Min Act: -0.0000

Data Index: 365447 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.5910. Min Act: -0.0000

Data Index: 1287645 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.5374. Min Act: -0.0000

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.4484. Min Act: -0.0000

Data Index: 1238899 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.4710. Min Act: -0.0000

Data Index: 1617554 (Python Code)

Max Activating Token Index: 707

Text #6

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.5491. Min Act: -0.0000

Data Index: 1640039 (Python Code)

Max Activating Token Index: 688

Text #7

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.2929. Min Act: -0.0000

Data Index: 917679 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.5057. Min Act: -0.0000

Data Index: 581063 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.1295. Min Act: -0.0000

Data Index: 365468 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.1198. Min Act: -0.0000

Data Index: 1579982 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.3676. Min Act: -0.0000

Data Index: 1162176 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.3271. Min Act: -0.0000

Data Index: 536551 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.4329. Min Act: -0.0000

Data Index: 1357469 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.1752. Min Act: -0.0000

Data Index: 1648169 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.1751. Min Act: -0.0000

Data Index: 1594512 (Python Code)

Max Activating Token Index: 876

Text #16

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.1563. Min Act: -0.0000

Data Index: 77975 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.2706. Min Act: -0.0000

Data Index: 1392219 (Python Code)

Max Activating Token Index: 657

Text #18

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.2689. Min Act: -0.0000

Data Index: 1420324 (Python Code)

Max Activating Token Index: 823

Text #19

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.1317. Min Act: -0.0000

Data Index: 1568821 (Python Code)

Max Activating Token Index: 633