Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1092 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1001739 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0001

Data Index: 355267 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0652. Min Act: -0.0001

Data Index: 705555 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0652. Min Act: -0.0001

Data Index: 582382 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0669. Min Act: -0.0001

Data Index: 50075 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0596. Min Act: -0.0001

Data Index: 190576 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1100577 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0553. Min Act: -0.0001

Data Index: 489034 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0609. Min Act: -0.0001

Data Index: 515335 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0621. Min Act: -0.0001

Data Index: 4632 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0576. Min Act: -0.0001

Data Index: 205579 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1050362 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0545. Min Act: -0.0001

Data Index: 995829 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0531. Min Act: -0.0001

Data Index: 359387 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0592. Min Act: -0.0001

Data Index: 289006 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1068299 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1095145 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0506. Min Act: -0.0001

Data Index: 714273 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1095310 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0482. Min Act: -0.0001

Data Index: 762181 (C4 (Web Text))

Max Activating Token Index: 783