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

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

Neuron 2247 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: 1.1433. Min Range: -1.1433

Max Act: 1.1433. Min Act: -0.0000

Data Index: 412703 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1471572 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1186642 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9226. Min Act: -0.0001

Data Index: 1343393 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1199098 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9073. Min Act: -0.0001

Data Index: 303915 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9463. Min Act: -0.0001

Data Index: 1185460 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9665. Min Act: -0.0000

Data Index: 540444 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8828. Min Act: -0.0000

Data Index: 50793 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8721. Min Act: -0.0000

Data Index: 264761 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1619403 (Python Code)

Max Activating Token Index: 858

Text #11

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8395. Min Act: -0.0000

Data Index: 683367 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8575. Min Act: -0.0000

Data Index: 130244 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8445. Min Act: -0.0001

Data Index: 769898 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8084. Min Act: -0.0000

Data Index: 979857 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8279. Min Act: -0.0000

Data Index: 105671 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7768. Min Act: -0.0000

Data Index: 823369 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8024. Min Act: -0.0000

Data Index: 394352 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1564831 (Python Code)

Max Activating Token Index: 585

Text #19

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1569571 (Python Code)

Max Activating Token Index: 788