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

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

Neuron 1948 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: 0.5840. Min Range: -0.5840

Max Act: 0.5840. Min Act: -0.0000

Data Index: 279582 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5456. Min Act: -0.0001

Data Index: 1325322 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5322. Min Act: -0.0000

Data Index: 443218 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4985. Min Act: -0.0000

Data Index: 980170 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4778. Min Act: -0.0000

Data Index: 388149 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4886. Min Act: -0.0000

Data Index: 671470 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1316131 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4498. Min Act: -0.0000

Data Index: 670215 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4724. Min Act: -0.0001

Data Index: 691691 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4435. Min Act: -0.0000

Data Index: 621571 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4529. Min Act: -0.0001

Data Index: 772698 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4369. Min Act: -0.0001

Data Index: 1049642 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4483. Min Act: -0.0000

Data Index: 720975 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1235215 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4392. Min Act: -0.0001

Data Index: 1306834 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4317. Min Act: -0.0001

Data Index: 725595 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4029. Min Act: -0.0001

Data Index: 730559 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1156592 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4149. Min Act: -0.0000

Data Index: 362033 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1151570 (C4 (Web Text))

Max Activating Token Index: 709