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

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

Neuron 2626 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.6447. Min Act: -0.0001

Data Index: 500850 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.3170. Min Act: -0.0001

Data Index: 226209 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.4858. Min Act: -0.0001

Data Index: 1031340 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5413. Min Act: -0.0001

Data Index: 350900 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5300. Min Act: -0.0001

Data Index: 1068649 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.3157. Min Act: -0.0001

Data Index: 344036 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.1570. Min Act: -0.0001

Data Index: 1354924 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.1778. Min Act: -0.0001

Data Index: 589567 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5705. Min Act: -0.0001

Data Index: 615453 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.9258. Min Act: -0.0001

Data Index: 1307490 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.9629. Min Act: -0.0001

Data Index: 1290172 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.5504. Min Act: -0.0001

Data Index: 1082844 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.9307. Min Act: -0.0001

Data Index: 33881 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.7707. Min Act: -0.0001

Data Index: 462650 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.7134. Min Act: -0.0001

Data Index: 1233880 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.8357. Min Act: -0.0001

Data Index: 657866 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.6999. Min Act: -0.0001

Data Index: 335067 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.8289. Min Act: -0.0001

Data Index: 336309 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.8002. Min Act: -0.0001

Data Index: 777860 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 3.6447. Min Range: -3.6447

Max Act: 2.7929. Min Act: -0.0001

Data Index: 575775 (C4 (Web Text))

Max Activating Token Index: 582