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

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

Neuron 1032 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: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0005

Data Index: 1003037 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0640. Min Act: -0.0005

Data Index: 744493 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0594. Min Act: -0.0005

Data Index: 952970 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0573. Min Act: -0.0005

Data Index: 513281 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0605. Min Act: -0.0005

Data Index: 466256 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0583. Min Act: -0.0005

Data Index: 488622 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0571. Min Act: -0.0005

Data Index: 1012442 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0555. Min Act: -0.0005

Data Index: 545127 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0546. Min Act: -0.0005

Data Index: 138692 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0540. Min Act: -0.0005

Data Index: 2507 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0581. Min Act: -0.0005

Data Index: 522241 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0536. Min Act: -0.0005

Data Index: 1025878 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0556. Min Act: -0.0005

Data Index: 611206 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0538. Min Act: -0.0005

Data Index: 592421 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0505. Min Act: -0.0005

Data Index: 386767 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0540. Min Act: -0.0005

Data Index: 819028 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0541. Min Act: -0.0005

Data Index: 1033257 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0516. Min Act: -0.0005

Data Index: 154641 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0546. Min Act: -0.0005

Data Index: 1168889 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0486. Min Act: -0.0005

Data Index: 671535 (C4 (Web Text))

Max Activating Token Index: 348