Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5751 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.8828. Min Act: -0.0001

Data Index: 584601 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7961. Min Act: -0.0001

Data Index: 528876 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7855. Min Act: -0.0001

Data Index: 1300288 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7679. Min Act: -0.0001

Data Index: 290698 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7634. Min Act: -0.0001

Data Index: 426915 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7613. Min Act: -0.0001

Data Index: 797625 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7672. Min Act: -0.0001

Data Index: 254724 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7504. Min Act: -0.0001

Data Index: 1014169 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7423. Min Act: -0.0001

Data Index: 609915 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7414. Min Act: -0.0001

Data Index: 848057 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7574. Min Act: -0.0001

Data Index: 700568 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7515. Min Act: -0.0001

Data Index: 136913 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7428. Min Act: -0.0001

Data Index: 796673 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7391. Min Act: -0.0001

Data Index: 568661 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7300. Min Act: -0.0001

Data Index: 335438 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7499. Min Act: -0.0001

Data Index: 174628 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7336. Min Act: -0.0001

Data Index: 212369 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1186600 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7331. Min Act: -0.0001

Data Index: 799821 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7375. Min Act: -0.0001

Data Index: 916070 (C4 (Web Text))

Max Activating Token Index: 78