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

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

Neuron 844 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.9436. Min Act: -0.0000

Data Index: 1612121 (Python Code)

Max Activating Token Index: 438

Text #1

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1532914 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.8140. Min Act: -0.0000

Data Index: 1435344 (Python Code)

Max Activating Token Index: 305

Text #3

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.8416. Min Act: -0.0000

Data Index: 1400112 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.6000. Min Act: -0.0000

Data Index: 1641568 (Python Code)

Max Activating Token Index: 278

Text #5

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1629690 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1370312 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1569801 (Python Code)

Max Activating Token Index: 1007

Text #8

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1522789 (Python Code)

Max Activating Token Index: 522

Text #9

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1468669 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1399113 (Python Code)

Max Activating Token Index: 872

Text #11

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1430336 (Python Code)

Max Activating Token Index: 663

Text #12

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.4582. Min Act: -0.0000

Data Index: 1440501 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.3619. Min Act: -0.0000

Data Index: 1467576 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.4450. Min Act: -0.0000

Data Index: 1582708 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1437245 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1411292 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1641470 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1482361 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 1.9436. Min Range: -1.9436

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1578348 (Python Code)

Max Activating Token Index: 157