Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 214 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1620448 (Python Code)

Max Activating Token Index: 159

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0362. Min Act: -0.0006

Data Index: 700481 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0270. Min Act: -0.0006

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1368412 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1587603 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1610130 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1533839 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0263. Min Act: -0.0006

Data Index: 650453 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1559829 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0260. Min Act: -0.0006

Data Index: 264740 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1128820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1585740 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0260. Min Act: -0.0006

Data Index: 80791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0198. Min Act: -0.0006

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1385715 (Python Code)

Max Activating Token Index: 222

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1504280 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1429963 (Python Code)

Max Activating Token Index: 875

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1356919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0237. Min Act: -0.0006

Data Index: 842411 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0243. Min Act: -0.0006

Data Index: 447619 (C4 (Web Text))

Max Activating Token Index: 982