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

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

Neuron 3890 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.6646. Min Act: -0.0000

Data Index: 19029 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.2444. Min Act: -0.0000

Data Index: 245180 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.2001. Min Act: -0.0000

Data Index: 878045 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.2560. Min Act: -0.0000

Data Index: 793240 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.2653. Min Act: -0.0000

Data Index: 551380 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.0448. Min Act: -0.0000

Data Index: 418280 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.1878. Min Act: -0.0000

Data Index: 780593 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.1938. Min Act: -0.0000

Data Index: 909845 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.2999. Min Act: -0.0000

Data Index: 1351749 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 5.6646. Min Range: -5.6646

Max Act: 4.9480. Min Act: -0.0000

Data Index: 508799 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.1399. Min Act: -0.0000

Data Index: 506582 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 5.6646. Min Range: -5.6646

Max Act: 4.9253. Min Act: -0.0000

Data Index: 1111843 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 5.6646. Min Range: -5.6646

Max Act: 4.8728. Min Act: -0.0000

Data Index: 591644 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 5.6646. Min Range: -5.6646

Max Act: 4.9542. Min Act: -0.0000

Data Index: 1014326 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 5.6646. Min Range: -5.6646

Max Act: 4.9452. Min Act: -0.0000

Data Index: 1081927 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.1350. Min Act: -0.0000

Data Index: 1316067 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 5.6646. Min Range: -5.6646

Max Act: 4.7580. Min Act: -0.0000

Data Index: 679771 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 5.6646. Min Range: -5.6646

Max Act: 4.9278. Min Act: -0.0000

Data Index: 1293044 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.1048. Min Act: -0.0000

Data Index: 1238841 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 5.6646. Min Range: -5.6646

Max Act: 5.1079. Min Act: -0.0000

Data Index: 1343842 (C4 (Web Text))

Max Activating Token Index: 1016