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

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

Neuron 867 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: 0.6825. Min Range: -0.6825

Max Act: 0.6825. Min Act: -0.0001

Data Index: 101940 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6736. Min Act: -0.0001

Data Index: 724981 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6338. Min Act: -0.0001

Data Index: 455255 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6081. Min Act: -0.0001

Data Index: 14479 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6234. Min Act: -0.0001

Data Index: 613619 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6254. Min Act: -0.0001

Data Index: 141605 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6075. Min Act: -0.0001

Data Index: 1341279 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6190. Min Act: -0.0001

Data Index: 642069 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6131. Min Act: -0.0001

Data Index: 372777 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5949. Min Act: -0.0001

Data Index: 479269 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6101. Min Act: -0.0001

Data Index: 50488 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5894. Min Act: -0.0001

Data Index: 1256997 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6049. Min Act: -0.0001

Data Index: 1104794 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5682. Min Act: -0.0001

Data Index: 290577 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6017. Min Act: -0.0001

Data Index: 1650089 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6045. Min Act: -0.0001

Data Index: 46580 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6032. Min Act: -0.0001

Data Index: 572028 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5606. Min Act: -0.0001

Data Index: 618469 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5740. Min Act: -0.0001

Data Index: 568652 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5790. Min Act: -0.0001

Data Index: 273738 (C4 (Web Text))

Max Activating Token Index: 831