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

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

Neuron 1386 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: 0.2499. Min Range: -0.2499

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1365321 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1590243 (Python Code)

Max Activating Token Index: 449

Text #2

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2289. Min Act: -0.0002

Data Index: 1371030 (Python Code)

Max Activating Token Index: 98

Text #3

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1370992 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1413801 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1395060 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1455595 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1641415 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2079. Min Act: -0.0002

Data Index: 1560788 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2013. Min Act: -0.0002

Data Index: 1590438 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1582656 (Python Code)

Max Activating Token Index: 406

Text #11

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1427289 (Python Code)

Max Activating Token Index: 711

Text #12

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2035. Min Act: -0.0001

Data Index: 1505475 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2013. Min Act: -0.0002

Data Index: 1527723 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1648520 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1965. Min Act: -0.0002

Data Index: 1527040 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1994. Min Act: -0.0001

Data Index: 1359856 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1390193 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1485453 (Python Code)

Max Activating Token Index: 267

Text #19

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1950. Min Act: -0.0002

Data Index: 1477994 (Python Code)

Max Activating Token Index: 378