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

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

Neuron 716 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0844. Min Act: -0.0001

Data Index: 800591 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1194409 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1071955 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0784. Min Act: -0.0001

Data Index: 112190 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0821. Min Act: -0.0001

Data Index: 366114 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1288799 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1260868 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0806. Min Act: -0.0001

Data Index: 312612 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0707. Min Act: -0.0001

Data Index: 265408 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0703. Min Act: -0.0001

Data Index: 147871 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0667. Min Act: -0.0001

Data Index: 536664 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0658. Min Act: -0.0001

Data Index: 336497 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1127555 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0665. Min Act: -0.0001

Data Index: 318411 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0709. Min Act: -0.0001

Data Index: 650209 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1306870 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0672. Min Act: -0.0001

Data Index: 555909 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0669. Min Act: -0.0001

Data Index: 513820 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0657. Min Act: -0.0001

Data Index: 980251 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0623. Min Act: -0.0001

Data Index: 820416 (C4 (Web Text))

Max Activating Token Index: 757