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

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

Neuron 3602 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: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0001

Data Index: 413844 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1016633 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0544. Min Act: -0.0001

Data Index: 536626 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1022921 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0512. Min Act: -0.0001

Data Index: 829251 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1282809 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1090426 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0499. Min Act: -0.0001

Data Index: 708140 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0489. Min Act: -0.0001

Data Index: 998337 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1304806 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1083017 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0476. Min Act: -0.0001

Data Index: 580284 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1017814 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0479. Min Act: -0.0001

Data Index: 28747 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0472. Min Act: -0.0001

Data Index: 100893 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0475. Min Act: -0.0001

Data Index: 149230 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0465. Min Act: -0.0001

Data Index: 686114 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0457. Min Act: -0.0001

Data Index: 755195 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0460. Min Act: -0.0001

Data Index: 578657 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0460. Min Act: -0.0001

Data Index: 248919 (C4 (Web Text))

Max Activating Token Index: 662