Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1666 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.8377. Min Act: -0.0000

Data Index: 1309263 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.6697. Min Act: -0.0000

Data Index: 515164 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.4575. Min Act: -0.0000

Data Index: 417557 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.2269. Min Act: -0.0000

Data Index: 1324054 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.2143. Min Act: -0.0000

Data Index: 192993 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1211433 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.1601. Min Act: -0.0000

Data Index: 105640 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.9732. Min Act: -0.0000

Data Index: 612480 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 2.8377. Min Range: -2.8377

Max Act: 2.0698. Min Act: -0.0000

Data Index: 57082 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.9706. Min Act: -0.0000

Data Index: 1089342 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.9194. Min Act: -0.0000

Data Index: 455784 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1049728 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.9271. Min Act: -0.0000

Data Index: 941522 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.8432. Min Act: -0.0000

Data Index: 730425 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.8035. Min Act: -0.0000

Data Index: 1340413 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.8234. Min Act: -0.0000

Data Index: 736743 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.8223. Min Act: 0.0000

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.7517. Min Act: -0.0000

Data Index: 910992 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.7947. Min Act: -0.0000

Data Index: 262192 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.8377. Min Range: -2.8377

Max Act: 1.7032. Min Act: -0.0000

Data Index: 318191 (C4 (Web Text))

Max Activating Token Index: 987