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

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

Neuron 3509 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: 1.6863. Min Range: -1.6863

Max Act: 1.6404. Min Act: -0.0002

Data Index: 1059696 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6306. Min Act: -0.0002

Data Index: 21759 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6109. Min Act: -0.0002

Data Index: 958574 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6863. Min Act: -0.0002

Data Index: 1247513 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5893. Min Act: -0.0002

Data Index: 1237649 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6473. Min Act: -0.0002

Data Index: 1014538 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5471. Min Act: -0.0002

Data Index: 709641 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5917. Min Act: -0.0002

Data Index: 1081055 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5364. Min Act: -0.0002

Data Index: 1004931 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5646. Min Act: -0.0002

Data Index: 1354 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6192. Min Act: -0.0002

Data Index: 408822 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5212. Min Act: -0.0002

Data Index: 79945 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5369. Min Act: -0.0002

Data Index: 1343080 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4847. Min Act: -0.0002

Data Index: 967036 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5381. Min Act: -0.0002

Data Index: 1268549 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4938. Min Act: -0.0002

Data Index: 240401 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5284. Min Act: -0.0002

Data Index: 917315 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4668. Min Act: -0.0002

Data Index: 15539 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4933. Min Act: -0.0002

Data Index: 579577 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5156. Min Act: -0.0002

Data Index: 473357 (C4 (Web Text))

Max Activating Token Index: 573