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

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

Neuron 257 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.8643. Min Act: -0.0000

Data Index: 502902 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.6965. Min Act: -0.0000

Data Index: 627634 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.6690. Min Act: -0.0000

Data Index: 15949 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1058117 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1170630 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4516. Min Act: -0.0000

Data Index: 701874 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1230569 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.5285. Min Act: -0.0000

Data Index: 332859 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4606. Min Act: -0.0000

Data Index: 817269 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1247368 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.5063. Min Act: -0.0000

Data Index: 240607 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4985. Min Act: -0.0000

Data Index: 913715 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4774. Min Act: -0.0000

Data Index: 652451 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4757. Min Act: -0.0000

Data Index: 921814 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4717. Min Act: -0.0000

Data Index: 162883 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1174998 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4649. Min Act: -0.0000

Data Index: 86250 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4531. Min Act: -0.0000

Data Index: 566364 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.4490. Min Act: -0.0000

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.8643. Min Range: -0.8643

Max Act: 0.5146. Min Act: -0.0000

Data Index: 962122 (C4 (Web Text))

Max Activating Token Index: 670