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

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

Neuron 3890 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0031. Min Range: -2.0031

Max Act: 2.0031. Min Act: -0.0001

Data Index: 1616959 (Python Code)

Max Activating Token Index: 800

Text #1

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1513715 (Python Code)

Max Activating Token Index: 861

Text #2

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1643713 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.6555. Min Act: -0.0001

Data Index: 1587996 (Python Code)

Max Activating Token Index: 987

Text #4

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.6445. Min Act: -0.0000

Data Index: 1656307 (Python Code)

Max Activating Token Index: 634

Text #5

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1536805 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.6269. Min Act: -0.0001

Data Index: 1589785 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.6332. Min Act: -0.0001

Data Index: 1632086 (Python Code)

Max Activating Token Index: 801

Text #8

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1389391 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.5661. Min Act: -0.0000

Data Index: 1453563 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.4863. Min Act: -0.0001

Data Index: 1390038 (Python Code)

Max Activating Token Index: 277

Text #11

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.6500. Min Act: -0.0001

Data Index: 1379093 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.4347. Min Act: -0.0000

Data Index: 1493434 (Python Code)

Max Activating Token Index: 648

Text #13

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.5098. Min Act: -0.0000

Data Index: 1653605 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.5475. Min Act: -0.0001

Data Index: 1388888 (Python Code)

Max Activating Token Index: 877

Text #15

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.4584. Min Act: -0.0000

Data Index: 1625157 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.5938. Min Act: -0.0001

Data Index: 1436925 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.4509. Min Act: -0.0000

Data Index: 1560054 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.5844. Min Act: -0.0000

Data Index: 1604759 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.4104. Min Act: -0.0001

Data Index: 1421443 (Python Code)

Max Activating Token Index: 304