Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0001

Data Index: 352089 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0656. Min Act: -0.0002

Data Index: 622606 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1031960 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0544. Min Act: -0.0002

Data Index: 292158 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0545. Min Act: -0.0002

Data Index: 646822 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0569. Min Act: -0.0002

Data Index: 65902 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0481. Min Act: -0.0002

Data Index: 462814 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0566. Min Act: -0.0002

Data Index: 728795 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1048621 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0542. Min Act: -0.0001

Data Index: 670287 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1337447 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0535. Min Act: -0.0001

Data Index: 448070 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0492. Min Act: -0.0002

Data Index: 343826 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0491. Min Act: -0.0002

Data Index: 983434 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0549. Min Act: -0.0001

Data Index: 143431 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0519. Min Act: -0.0002

Data Index: 203685 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0468. Min Act: -0.0001

Data Index: 962469 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1160485 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0493. Min Act: -0.0002

Data Index: 670573 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0513. Min Act: -0.0001

Data Index: 614926 (C4 (Web Text))

Max Activating Token Index: 586