Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1264394 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0631. Min Act: -0.0003

Data Index: 826369 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0635. Min Act: -0.0003

Data Index: 916784 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1317914 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1339631 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0450. Min Act: -0.0003

Data Index: 790847 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0546. Min Act: -0.0003

Data Index: 933595 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0505. Min Act: -0.0003

Data Index: 978829 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0535. Min Act: -0.0003

Data Index: 158019 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0521. Min Act: -0.0002

Data Index: 219503 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0527. Min Act: -0.0003

Data Index: 830139 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0489. Min Act: -0.0003

Data Index: 336698 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0495. Min Act: -0.0003

Data Index: 175468 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0511. Min Act: -0.0003

Data Index: 490746 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0499. Min Act: -0.0003

Data Index: 758879 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0458. Min Act: -0.0003

Data Index: 157186 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0487. Min Act: -0.0002

Data Index: 705278 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1082767 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0491. Min Act: -0.0003

Data Index: 394586 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0513. Min Act: -0.0003

Data Index: 903973 (C4 (Web Text))

Max Activating Token Index: 568