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

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

Neuron 551 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1465 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.0023. Min Range: -1.0023

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1039171 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.9623. Min Act: -0.0000

Data Index: 814014 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.9235. Min Act: -0.0001

Data Index: 482206 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.9028. Min Act: -0.0001

Data Index: 729943 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.9031. Min Act: -0.0000

Data Index: 882911 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8843. Min Act: -0.0000

Data Index: 932144 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.9546. Min Act: -0.0000

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.9028. Min Act: -0.0000

Data Index: 747109 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1198070 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8551. Min Act: -0.0000

Data Index: 906577 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8450. Min Act: -0.0000

Data Index: 639339 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8388. Min Act: -0.0000

Data Index: 852462 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8377. Min Act: -0.0000

Data Index: 241942 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8126. Min Act: -0.0000

Data Index: 705785 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8789. Min Act: -0.0000

Data Index: 422457 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8589. Min Act: -0.0000

Data Index: 439096 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8300. Min Act: -0.0000

Data Index: 724097 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8226. Min Act: -0.0000

Data Index: 288169 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.0023. Min Range: -1.0023

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1017007 (C4 (Web Text))

Max Activating Token Index: 463