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

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

Neuron 1970 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2141. Min Range: -1.2141

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1605530 (Python Code)

Max Activating Token Index: 491

Text #1

Max Range: 1.2141. Min Range: -1.2141

Max Act: 1.1425. Min Act: -0.0000

Data Index: 43871 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 1.2141. Min Range: -1.2141

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1344512 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.2141. Min Range: -1.2141

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1621236 (Python Code)

Max Activating Token Index: 807

Text #4

Max Range: 1.2141. Min Range: -1.2141

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1423722 (Python Code)

Max Activating Token Index: 1019

Text #5

Max Range: 1.2141. Min Range: -1.2141

Max Act: 1.0160. Min Act: -0.0000

Data Index: 195701 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1487256 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8943. Min Act: -0.0000

Data Index: 445622 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1623411 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.9392. Min Act: -0.0000

Data Index: 172201 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1113405 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1445013 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1442552 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1363243 (Python Code)

Max Activating Token Index: 814

Text #14

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1512213 (Python Code)

Max Activating Token Index: 670

Text #15

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1007752 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.7882. Min Act: -0.0001

Data Index: 1448825 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1616514 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1612644 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 1.2141. Min Range: -1.2141

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1598997 (Python Code)

Max Activating Token Index: 986