Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2697 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.6833. Min Act: -0.0001

Data Index: 1227424 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.6647. Min Act: -0.0001

Data Index: 846983 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5941. Min Act: -0.0001

Data Index: 1309584 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5300. Min Act: -0.0001

Data Index: 189642 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5738. Min Act: -0.0001

Data Index: 674149 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5463. Min Act: -0.0001

Data Index: 730543 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5383. Min Act: -0.0001

Data Index: 1162511 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5367. Min Act: -0.0001

Data Index: 864557 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5040. Min Act: -0.0001

Data Index: 470478 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4994. Min Act: -0.0001

Data Index: 395915 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1175309 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5007. Min Act: -0.0001

Data Index: 250678 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4704. Min Act: -0.0001

Data Index: 832333 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4979. Min Act: -0.0001

Data Index: 834988 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4990. Min Act: -0.0001

Data Index: 527806 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4702. Min Act: -0.0001

Data Index: 872135 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4365. Min Act: -0.0001

Data Index: 910575 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4842. Min Act: -0.0001

Data Index: 632952 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4484. Min Act: -0.0001

Data Index: 179896 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4938. Min Act: -0.0001

Data Index: 1328070 (C4 (Web Text))

Max Activating Token Index: 564