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

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

Neuron 3434 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3654. Min Range: -1.3654

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1229252 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.3654. Min Range: -1.3654

Max Act: 1.3654. Min Act: -0.0000

Data Index: 574464 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.3654. Min Range: -1.3654

Max Act: 1.1874. Min Act: -0.0000

Data Index: 471837 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1004364 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.3654. Min Range: -1.3654

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1261258 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.3654. Min Range: -1.3654

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1159204 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.3654. Min Range: -1.3654

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1335256 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.8450. Min Act: -0.0000

Data Index: 377153 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1290477 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.8126. Min Act: -0.0000

Data Index: 368677 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1103908 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.7663. Min Act: -0.0000

Data Index: 52747 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.7707. Min Act: -0.0000

Data Index: 693245 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.8402. Min Act: -0.0000

Data Index: 892298 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.7621. Min Act: -0.0000

Data Index: 134856 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.7032. Min Act: -0.0000

Data Index: 385957 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.7833. Min Act: -0.0000

Data Index: 836731 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.7448. Min Act: -0.0000

Data Index: 532232 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.6888. Min Act: -0.0000

Data Index: 64889 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 1.3654. Min Range: -1.3654

Max Act: 0.7203. Min Act: -0.0000

Data Index: 621455 (C4 (Web Text))

Max Activating Token Index: 790