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

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

Neuron 4543 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.1961. Min Act: 0.0001

Data Index: 1448595 (Python Code)

Max Activating Token Index: 369

Text #1

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1368144 (Python Code)

Max Activating Token Index: 467

Text #2

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1499258 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1651810 (Python Code)

Max Activating Token Index: 734

Text #4

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1454513 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1536818 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1603645 (Python Code)

Max Activating Token Index: 570

Text #7

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1548194 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1643805 (Python Code)

Max Activating Token Index: 777

Text #9

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1650557 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8821. Min Act: 0.0001

Data Index: 1571330 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1410241 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1461340 (Python Code)

Max Activating Token Index: 155

Text #13

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1630608 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1624373 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1554114 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1481410 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1481354 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1562176 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1463105 (Python Code)

Max Activating Token Index: 172