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

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

Neuron 3770 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2547. Min Range: -1.2547

Max Act: 1.2547. Min Act: -0.0000

Data Index: 990538 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.2547. Min Range: -1.2547

Max Act: 1.2502. Min Act: -0.0000

Data Index: 11260 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 1.2547. Min Range: -1.2547

Max Act: 1.1653. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.2547. Min Range: -1.2547

Max Act: 1.1325. Min Act: -0.0000

Data Index: 244171 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 1.2547. Min Range: -1.2547

Max Act: 1.1210. Min Act: -0.0000

Data Index: 873988 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1481268 (Python Code)

Max Activating Token Index: 877

Text #6

Max Range: 1.2547. Min Range: -1.2547

Max Act: 1.0637. Min Act: -0.0000

Data Index: 524768 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.2547. Min Range: -1.2547

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1119508 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1033320 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1077096 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.9210. Min Act: -0.0000

Data Index: 483500 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.9538. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.8476. Min Act: -0.0000

Data Index: 233487 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.8468. Min Act: -0.0000

Data Index: 157272 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.8667. Min Act: -0.0000

Data Index: 747469 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.8343. Min Act: -0.0000

Data Index: 811338 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.8745. Min Act: -0.0000

Data Index: 569752 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1520936 (Python Code)

Max Activating Token Index: 400

Text #18

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1265766 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 1.2547. Min Range: -1.2547

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1046963 (C4 (Web Text))

Max Activating Token Index: 512