Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 645 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1318732 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0599. Min Act: -0.0003

Data Index: 311464 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1165421 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0626. Min Act: -0.0003

Data Index: 172118 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1577933 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0597. Min Act: -0.0003

Data Index: 697978 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0602. Min Act: -0.0002

Data Index: 360190 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0590. Min Act: -0.0003

Data Index: 465135 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0595. Min Act: -0.0003

Data Index: 589766 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0580. Min Act: -0.0004

Data Index: 210589 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0555. Min Act: 0.0000

Data Index: 277900 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0572. Min Act: -0.0001

Data Index: 487985 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0553. Min Act: -0.0003

Data Index: 84093 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0559. Min Act: -0.0002

Data Index: 82877 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1136023 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0540. Min Act: -0.0003

Data Index: 770215 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0545. Min Act: -0.0002

Data Index: 46702 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0555. Min Act: -0.0003

Data Index: 335444 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0544. Min Act: -0.0003

Data Index: 274834 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1078158 (C4 (Web Text))

Max Activating Token Index: 850