Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2435 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1280729 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1259879 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5562. Min Act: -0.0000

Data Index: 103437 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6033. Min Act: -0.0000

Data Index: 361540 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5435. Min Act: 0.0000

Data Index: 1154075 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5424. Min Act: -0.0000

Data Index: 415294 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5678. Min Act: -0.0000

Data Index: 595042 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1331366 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5214. Min Act: -0.0000

Data Index: 697759 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5372. Min Act: -0.0000

Data Index: 230468 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5366. Min Act: -0.0000

Data Index: 328588 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.4918. Min Act: -0.0000

Data Index: 69590 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.4940. Min Act: -0.0000

Data Index: 485641 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1207974 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5041. Min Act: -0.0000

Data Index: 503568 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.4889. Min Act: -0.0000

Data Index: 931822 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.4824. Min Act: -0.0000

Data Index: 430945 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.4762. Min Act: -0.0000

Data Index: 739442 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.4765. Min Act: -0.0000

Data Index: 173249 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.4627. Min Act: -0.0000

Data Index: 520036 (C4 (Web Text))

Max Activating Token Index: 717