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

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

Neuron 4366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.9235. Min Act: -0.0000

Data Index: 944385 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.9266. Min Act: -0.0000

Data Index: 535719 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7895. Min Act: -0.0000

Data Index: 117776 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1340771 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8118. Min Act: -0.0000

Data Index: 478713 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7810. Min Act: -0.0000

Data Index: 709229 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7888. Min Act: -0.0000

Data Index: 36094 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7355. Min Act: -0.0000

Data Index: 441417 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1392705 (Python Code)

Max Activating Token Index: 954

Text #9

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1591474 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1270172 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7377. Min Act: -0.0000

Data Index: 712093 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7089. Min Act: -0.0000

Data Index: 243090 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1160102 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7050. Min Act: -0.0000

Data Index: 859296 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7479. Min Act: -0.0000

Data Index: 224647 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1226536 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7225. Min Act: -0.0000

Data Index: 116219 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.6962. Min Act: -0.0000

Data Index: 692295 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7125. Min Act: -0.0000

Data Index: 26426 (C4 (Web Text))

Max Activating Token Index: 884