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

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

Neuron 3293 in Layer 1

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: 3.1681. Min Range: -3.1681

Max Act: 3.1681. Min Act: -0.0002

Data Index: 436382 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 3.1681. Min Range: -3.1681

Max Act: 3.0558. Min Act: -0.0002

Data Index: 998364 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9621. Min Act: -0.0002

Data Index: 1204781 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9561. Min Act: -0.0002

Data Index: 959929 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9345. Min Act: -0.0002

Data Index: 300625 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9397. Min Act: -0.0002

Data Index: 555207 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9143. Min Act: -0.0002

Data Index: 1109479 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8507. Min Act: -0.0002

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8245. Min Act: -0.0002

Data Index: 1086331 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8993. Min Act: -0.0002

Data Index: 69975 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8933. Min Act: -0.0002

Data Index: 808595 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.7960. Min Act: -0.0002

Data Index: 43481 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8130. Min Act: -0.0002

Data Index: 583256 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8584. Min Act: -0.0002

Data Index: 249558 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.7704. Min Act: -0.0002

Data Index: 460086 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8528. Min Act: -0.0002

Data Index: 1298752 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.7897. Min Act: -0.0002

Data Index: 663614 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.7608. Min Act: -0.0002

Data Index: 1277671 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8443. Min Act: -0.0002

Data Index: 749448 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.7392. Min Act: -0.0002

Data Index: 626135 (C4 (Web Text))

Max Activating Token Index: 1008