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

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

Neuron 596 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: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1506976 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0473. Min Act: -0.0002

Data Index: 866239 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0452. Min Act: -0.0002

Data Index: 194834 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0450. Min Act: -0.0002

Data Index: 583322 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0446. Min Act: -0.0002

Data Index: 719609 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0437. Min Act: -0.0002

Data Index: 163103 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1032364 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1447964 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0433. Min Act: -0.0002

Data Index: 972619 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0428. Min Act: -0.0002

Data Index: 205571 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0423. Min Act: -0.0002

Data Index: 674420 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1591671 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0422. Min Act: -0.0002

Data Index: 46043 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0429. Min Act: -0.0002

Data Index: 124674 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1202864 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0420. Min Act: -0.0002

Data Index: 467748 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0418. Min Act: -0.0002

Data Index: 39171 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0414. Min Act: -0.0002

Data Index: 937032 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0424. Min Act: -0.0002

Data Index: 150599 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1328584 (C4 (Web Text))

Max Activating Token Index: 597