Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4550 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3127. Min Range: -2.3127

Max Act: 2.3127. Min Act: -0.0000

Data Index: 526238 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.2175. Min Act: -0.0000

Data Index: 71501 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1345491 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0692. Min Act: -0.0000

Data Index: 556894 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0654. Min Act: 0.0000

Data Index: 272896 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1292910 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0622. Min Act: -0.0000

Data Index: 286110 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0537. Min Act: -0.0000

Data Index: 267869 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1307313 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1088407 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0569. Min Act: -0.0000

Data Index: 417080 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0585. Min Act: -0.0000

Data Index: 798713 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0541. Min Act: -0.0000

Data Index: 270580 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0537. Min Act: -0.0000

Data Index: 583228 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0548. Min Act: -0.0000

Data Index: 652804 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0544. Min Act: -0.0000

Data Index: 185332 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1338075 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0516. Min Act: -0.0000

Data Index: 70554 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0507. Min Act: -0.0000

Data Index: 244556 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 2.3127. Min Range: -2.3127

Max Act: 0.0533. Min Act: -0.0000

Data Index: 668714 (C4 (Web Text))

Max Activating Token Index: 756