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

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

Neuron 3611 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.8416. Min Act: -0.0001

Data Index: 1533350 (Python Code)

Max Activating Token Index: 247

Text #1

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1469707 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1404231 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1630222 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1434719 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1386510 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1645774 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1508646 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1428633 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1449618 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6870. Min Act: -0.0001

Data Index: 1366622 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1423151 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1467265 (Python Code)

Max Activating Token Index: 655

Text #13

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1456844 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1384325 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1493021 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1435411 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1552049 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1610391 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1629201 (Python Code)

Max Activating Token Index: 538