Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6384. Min Act: -0.0000

Data Index: 1304622 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.1689. Min Act: -0.0000

Data Index: 1040950 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.1357. Min Act: -0.0000

Data Index: 1414146 (Python Code)

Max Activating Token Index: 893

Text #3

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.1158. Min Act: -0.0000

Data Index: 1587575 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.8989. Min Act: -0.0000

Data Index: 1526040 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.0299. Min Act: -0.0000

Data Index: 1017769 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.3615. Min Act: -0.0000

Data Index: 157711 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.9406. Min Act: -0.0000

Data Index: 1563744 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.9420. Min Act: -0.0000

Data Index: 418566 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.9696. Min Act: -0.0000

Data Index: 1455625 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.9370. Min Act: -0.0000

Data Index: 1083276 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.6303. Min Act: -0.0000

Data Index: 1505481 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.6653. Min Act: -0.0000

Data Index: 823721 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.4767. Min Act: -0.0000

Data Index: 988729 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.4626. Min Act: -0.0000

Data Index: 595327 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.4446. Min Act: -0.0000

Data Index: 1631289 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.4402. Min Act: -0.0000

Data Index: 1542343 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.4340. Min Act: -0.0000

Data Index: 130955 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.4261. Min Act: -0.0000

Data Index: 1478287 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 3.6384. Min Range: -3.6384

Max Act: 2.4136. Min Act: -0.0000

Data Index: 336095 (C4 (Web Text))

Max Activating Token Index: 957