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

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

Neuron 272 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2501. Min Act: -0.0002

Data Index: 896837 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2076. Min Act: -0.0001

Data Index: 286721 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2206. Min Act: -0.0002

Data Index: 783381 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2212. Min Act: -0.0001

Data Index: 911189 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1781. Min Act: -0.0002

Data Index: 987303 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1764. Min Act: -0.0001

Data Index: 238947 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1868. Min Act: -0.0001

Data Index: 1189387 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1252804 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1313107 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2062. Min Act: -0.0002

Data Index: 402439 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1096491 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1578445 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1453967 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1932. Min Act: -0.0001

Data Index: 121103 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1922. Min Act: -0.0001

Data Index: 869756 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1510642 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1819. Min Act: -0.0001

Data Index: 39273 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1494624 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1481162 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1505624 (Python Code)

Max Activating Token Index: 731