Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1893 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0004

Data Index: 753332 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0568. Min Act: -0.0003

Data Index: 394437 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1133552 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0572. Min Act: -0.0004

Data Index: 736534 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0556. Min Act: -0.0003

Data Index: 950072 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0566. Min Act: -0.0003

Data Index: 255939 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1079898 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0569. Min Act: -0.0003

Data Index: 698460 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1078141 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0556. Min Act: -0.0003

Data Index: 805825 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0548. Min Act: -0.0003

Data Index: 677421 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0525. Min Act: -0.0003

Data Index: 281649 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0544. Min Act: -0.0002

Data Index: 241135 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0519. Min Act: -0.0003

Data Index: 907919 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0531. Min Act: -0.0003

Data Index: 522218 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0518. Min Act: -0.0003

Data Index: 539904 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0519. Min Act: -0.0003

Data Index: 671790 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1141908 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0503. Min Act: -0.0003

Data Index: 38376 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0520. Min Act: -0.0003

Data Index: 189508 (C4 (Web Text))

Max Activating Token Index: 178