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

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

Neuron 1694 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: 1.0270. Min Range: -1.0270

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1131540 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0135. Min Act: -0.0000

Data Index: 283590 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8979. Min Act: 0.0000

Data Index: 884544 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8627. Min Act: -0.0000

Data Index: 675763 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8730. Min Act: 0.0000

Data Index: 137436 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8660. Min Act: 0.0000

Data Index: 555800 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1228779 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8542. Min Act: -0.0000

Data Index: 439983 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1029991 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8413. Min Act: -0.0000

Data Index: 973984 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8118. Min Act: -0.0000

Data Index: 48377 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7706. Min Act: 0.0000

Data Index: 601962 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7665. Min Act: -0.0000

Data Index: 644711 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6788. Min Act: -0.0000

Data Index: 870290 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7590. Min Act: -0.0000

Data Index: 400595 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7135. Min Act: -0.0000

Data Index: 170628 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7467. Min Act: -0.0000

Data Index: 109257 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1143347 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6994. Min Act: -0.0000

Data Index: 553552 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7819. Min Act: 0.0000

Data Index: 1055826 (C4 (Web Text))

Max Activating Token Index: 473