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

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

Neuron 656 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: 0.0683. Min Range: -0.0683

Max Act: 0.0683. Min Act: -0.0001

Data Index: 71457 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0604. Min Act: -0.0001

Data Index: 873315 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0592. Min Act: -0.0001

Data Index: 548669 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0581. Min Act: -0.0001

Data Index: 270327 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0567. Min Act: -0.0001

Data Index: 605511 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0501. Min Act: -0.0001

Data Index: 245871 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1225405 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0571. Min Act: -0.0001

Data Index: 332214 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0514. Min Act: -0.0001

Data Index: 191302 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0505. Min Act: -0.0001

Data Index: 258454 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0530. Min Act: -0.0001

Data Index: 949146 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0504. Min Act: -0.0001

Data Index: 386852 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0539. Min Act: -0.0001

Data Index: 475582 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1260452 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0481. Min Act: -0.0001

Data Index: 108967 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1245678 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0552. Min Act: -0.0001

Data Index: 577965 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0486. Min Act: -0.0001

Data Index: 904671 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0548. Min Act: -0.0001

Data Index: 846056 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0510. Min Act: -0.0001

Data Index: 407402 (C4 (Web Text))

Max Activating Token Index: 700