Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1298 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1264362 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1255968 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0646. Min Act: -0.0000

Data Index: 265627 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0617. Min Act: -0.0000

Data Index: 566019 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0604. Min Act: -0.0000

Data Index: 44200 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1181713 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0522. Min Act: -0.0000

Data Index: 893974 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0540. Min Act: -0.0000

Data Index: 52756 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0467. Min Act: -0.0000

Data Index: 314504 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1510609 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0444. Min Act: -0.0000

Data Index: 882472 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0451. Min Act: -0.0000

Data Index: 915888 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1139497 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0406. Min Act: -0.0000

Data Index: 872006 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0412. Min Act: -0.0000

Data Index: 159095 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0385. Min Act: -0.0000

Data Index: 290917 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0332. Min Act: 0.0000

Data Index: 998727 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0368. Min Act: -0.0000

Data Index: 603644 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1055354 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1443497 (Python Code)

Max Activating Token Index: 698