Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1467417 (Python Code)

Max Activating Token Index: 258

Text #1

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4523. Min Act: -0.0001

Data Index: 1572968 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4396. Min Act: -0.0001

Data Index: 1647925 (Python Code)

Max Activating Token Index: 921

Text #3

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4143. Min Act: -0.0001

Data Index: 1570667 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4292. Min Act: -0.0001

Data Index: 1625594 (Python Code)

Max Activating Token Index: 410

Text #5

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1648828 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4420. Min Act: -0.0001

Data Index: 1535526 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1615493 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1430336 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4365. Min Act: -0.0001

Data Index: 1590532 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4486. Min Act: -0.0001

Data Index: 1605220 (Python Code)

Max Activating Token Index: 938

Text #11

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1426580 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4183. Min Act: -0.0001

Data Index: 1508227 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4329. Min Act: -0.0001

Data Index: 1440835 (Python Code)

Max Activating Token Index: 815

Text #14

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1629040 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4394. Min Act: -0.0001

Data Index: 1558894 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4228. Min Act: -0.0001

Data Index: 1387402 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4083. Min Act: -0.0001

Data Index: 1370165 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1445820 (Python Code)

Max Activating Token Index: 950

Text #19

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4194. Min Act: -0.0001

Data Index: 1564694 (Python Code)

Max Activating Token Index: 796