Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1728 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0000

Data Index: 897903 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1052171 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7164. Min Act: -0.0000

Data Index: 598132 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7092. Min Act: -0.0000

Data Index: 100123 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7283. Min Act: -0.0000

Data Index: 234012 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7765. Min Act: -0.0000

Data Index: 724575 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6538. Min Act: -0.0000

Data Index: 950152 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7131. Min Act: -0.0000

Data Index: 954538 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6407. Min Act: -0.0000

Data Index: 515223 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6303. Min Act: -0.0000

Data Index: 785513 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7082. Min Act: -0.0000

Data Index: 943156 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6740. Min Act: 0.0000

Data Index: 680203 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6752. Min Act: -0.0000

Data Index: 119015 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1029307 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6624. Min Act: -0.0000

Data Index: 325514 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6907. Min Act: -0.0000

Data Index: 29676 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6288. Min Act: -0.0000

Data Index: 318470 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6040. Min Act: -0.0000

Data Index: 514005 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6154. Min Act: -0.0000

Data Index: 48476 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6190. Min Act: -0.0000

Data Index: 33786 (C4 (Web Text))

Max Activating Token Index: 800