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

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

Neuron 4036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0002

Data Index: 583958 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0496. Min Act: -0.0002

Data Index: 470226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0525. Min Act: -0.0002

Data Index: 911872 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1056608 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1342503 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0510. Min Act: -0.0002

Data Index: 426715 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1293858 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0480. Min Act: -0.0002

Data Index: 443200 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0494. Min Act: -0.0002

Data Index: 947251 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0495. Min Act: -0.0002

Data Index: 927737 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0531. Min Act: -0.0002

Data Index: 200618 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0462. Min Act: -0.0002

Data Index: 538545 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0499. Min Act: -0.0002

Data Index: 774927 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1215836 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0484. Min Act: -0.0002

Data Index: 807733 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1184183 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1202814 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0454. Min Act: -0.0002

Data Index: 917213 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0432. Min Act: -0.0002

Data Index: 510246 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0493. Min Act: -0.0002

Data Index: 397868 (C4 (Web Text))

Max Activating Token Index: 715