Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1338 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0005

Data Index: 1535352 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0652. Min Act: -0.0005

Data Index: 1159592 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0607. Min Act: -0.0005

Data Index: 24048 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0592. Min Act: -0.0005

Data Index: 1397108 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0583. Min Act: -0.0005

Data Index: 1046367 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0555. Min Act: -0.0005

Data Index: 281910 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0563. Min Act: -0.0005

Data Index: 16891 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0528. Min Act: -0.0005

Data Index: 598123 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0527. Min Act: -0.0005

Data Index: 937893 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0565. Min Act: -0.0005

Data Index: 1414085 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0555. Min Act: -0.0005

Data Index: 32027 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0506. Min Act: -0.0005

Data Index: 1414932 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0553. Min Act: -0.0005

Data Index: 490454 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0512. Min Act: -0.0005

Data Index: 1016027 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0521. Min Act: -0.0005

Data Index: 557674 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0488. Min Act: -0.0005

Data Index: 727082 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0550. Min Act: -0.0005

Data Index: 759889 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0578. Min Act: -0.0005

Data Index: 27254 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0514. Min Act: -0.0005

Data Index: 468053 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0561. Min Act: -0.0005

Data Index: 1464618 (Python Code)

Max Activating Token Index: 884