Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 60 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0003

Data Index: 617626 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0597. Min Act: -0.0003

Data Index: 165912 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0584. Min Act: -0.0003

Data Index: 558696 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0552. Min Act: -0.0004

Data Index: 304425 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0550. Min Act: -0.0003

Data Index: 22800 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0537. Min Act: -0.0003

Data Index: 658793 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0546. Min Act: -0.0003

Data Index: 542639 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1271665 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0548. Min Act: -0.0003

Data Index: 481718 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0537. Min Act: -0.0003

Data Index: 339923 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0525. Min Act: -0.0003

Data Index: 229449 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0510. Min Act: -0.0003

Data Index: 838230 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0526. Min Act: -0.0003

Data Index: 877158 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0504. Min Act: -0.0003

Data Index: 687750 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0526. Min Act: -0.0003

Data Index: 143595 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0518. Min Act: -0.0003

Data Index: 38873 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0510. Min Act: -0.0003

Data Index: 432043 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0489. Min Act: -0.0003

Data Index: 637917 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0521. Min Act: -0.0003

Data Index: 934588 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0497. Min Act: -0.0003

Data Index: 47114 (C4 (Web Text))

Max Activating Token Index: 471