Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2389 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1694. Min Act: -0.0001

Data Index: 1648455 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1454497 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1415540 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0941. Min Act: -0.0001

Data Index: 1546963 (Python Code)

Max Activating Token Index: 264

Text #4

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0381. Min Act: -0.0001

Data Index: 1534551 (Python Code)

Max Activating Token Index: 657

Text #5

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0515. Min Act: -0.0001

Data Index: 1549060 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1529001 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0083. Min Act: -0.0001

Data Index: 1569334 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0212. Min Act: -0.0001

Data Index: 47262 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0128. Min Act: -0.0001

Data Index: 1654240 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0088. Min Act: -0.0000

Data Index: 339363 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0298. Min Act: -0.0001

Data Index: 1369860 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1526159 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1480357 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9968. Min Act: -0.0001

Data Index: 1606716 (Python Code)

Max Activating Token Index: 485

Text #15

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1428000 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1616821 (Python Code)

Max Activating Token Index: 694

Text #17

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1507114 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9757. Min Act: -0.0001

Data Index: 21289 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1370454 (Python Code)

Max Activating Token Index: 802