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

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

Neuron 3824 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1491735 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1587518 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1612822 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1451452 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1515747 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1568261 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1389506 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1430598 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1588772 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1611991 (Python Code)

Max Activating Token Index: 774

Text #10

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1624961 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1611411 (Python Code)

Max Activating Token Index: 211

Text #12

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1519877 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1623418 (Python Code)

Max Activating Token Index: 845

Text #14

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1459934 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1364457 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1516934 (Python Code)

Max Activating Token Index: 563

Text #17

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1383225 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1445481 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1576779 (Python Code)

Max Activating Token Index: 384