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

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

Neuron 274 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: 1.9135. Min Range: -1.9135

Max Act: 1.9135. Min Act: -0.0000

Data Index: 14005 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.8185. Min Act: -0.0000

Data Index: 22664 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.8107. Min Act: -0.0000

Data Index: 959411 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.7535. Min Act: -0.0000

Data Index: 1362572 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.6589. Min Act: -0.0000

Data Index: 357 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.6773. Min Act: -0.0000

Data Index: 346678 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.6407. Min Act: -0.0000

Data Index: 424269 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.6240. Min Act: -0.0000

Data Index: 1033485 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.5333. Min Act: -0.0000

Data Index: 9988 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.5793. Min Act: -0.0000

Data Index: 445329 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.6375. Min Act: -0.0000

Data Index: 616113 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.4799. Min Act: -0.0000

Data Index: 690896 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.5396. Min Act: -0.0000

Data Index: 282493 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.5258. Min Act: -0.0000

Data Index: 898592 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.4753. Min Act: -0.0000

Data Index: 354673 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1641473 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1000006 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.4097. Min Act: -0.0000

Data Index: 1337476 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.4888. Min Act: -0.0000

Data Index: 985939 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.9135. Min Range: -1.9135

Max Act: 1.4675. Min Act: -0.0000

Data Index: 390463 (C4 (Web Text))

Max Activating Token Index: 841