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

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

Neuron 885 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: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0005

Data Index: 1265531 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0575. Min Act: -0.0005

Data Index: 1048010 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0602. Min Act: -0.0005

Data Index: 675325 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0575. Min Act: -0.0005

Data Index: 232491 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0562. Min Act: -0.0005

Data Index: 987139 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0555. Min Act: -0.0005

Data Index: 86529 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0544. Min Act: -0.0005

Data Index: 283909 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0545. Min Act: -0.0005

Data Index: 1309421 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0486. Min Act: -0.0005

Data Index: 1464506 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0565. Min Act: -0.0005

Data Index: 760901 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0549. Min Act: -0.0005

Data Index: 29539 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0555. Min Act: -0.0005

Data Index: 739907 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0546. Min Act: -0.0005

Data Index: 589596 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0528. Min Act: -0.0005

Data Index: 396629 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0548. Min Act: -0.0005

Data Index: 334337 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0518. Min Act: -0.0005

Data Index: 1255745 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0536. Min Act: -0.0005

Data Index: 1022228 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0541. Min Act: -0.0005

Data Index: 744533 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0553. Min Act: -0.0005

Data Index: 127206 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0521. Min Act: -0.0005

Data Index: 15690 (C4 (Web Text))

Max Activating Token Index: 198