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

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

Neuron 2213 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.9647. Min Act: -0.0000

Data Index: 1429375 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.6621. Min Act: -0.0000

Data Index: 646202 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.4851. Min Act: -0.0000

Data Index: 1635382 (Python Code)

Max Activating Token Index: 707

Text #3

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1495235 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3469. Min Act: -0.0000

Data Index: 1530370 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3799. Min Act: -0.0000

Data Index: 1384045 (Python Code)

Max Activating Token Index: 345

Text #6

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3178. Min Act: -0.0000

Data Index: 1367672 (Python Code)

Max Activating Token Index: 896

Text #7

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1517865 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1550069 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1618408 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3607. Min Act: -0.0000

Data Index: 208132 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3171. Min Act: -0.0000

Data Index: 678567 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1151864 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.3140. Min Act: -0.0000

Data Index: 365958 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1419003 (Python Code)

Max Activating Token Index: 862

Text #15

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.2387. Min Act: -0.0000

Data Index: 251011 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1564999 (Python Code)

Max Activating Token Index: 543

Text #17

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1559922 (Python Code)

Max Activating Token Index: 636

Text #18

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1186554 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 1.9647. Min Range: -1.9647

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1642778 (Python Code)

Max Activating Token Index: 1015