Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2516 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0001

Data Index: 417689 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0661. Min Act: -0.0001

Data Index: 714945 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1019694 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0629. Min Act: -0.0001

Data Index: 372541 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1653561 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1431027 (Python Code)

Max Activating Token Index: 422

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0637. Min Act: -0.0001

Data Index: 739945 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0602. Min Act: -0.0001

Data Index: 346811 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0604. Min Act: -0.0001

Data Index: 674761 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0605. Min Act: -0.0001

Data Index: 194669 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0640. Min Act: -0.0001

Data Index: 511722 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0635. Min Act: -0.0001

Data Index: 358394 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1576653 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1130981 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1487400 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0586. Min Act: -0.0001

Data Index: 60980 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0581. Min Act: -0.0001

Data Index: 35211 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1015930 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0596. Min Act: -0.0001

Data Index: 949760 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0625. Min Act: -0.0001

Data Index: 323946 (C4 (Web Text))

Max Activating Token Index: 557