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

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

Neuron 500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3284. Min Range: -2.3284

Max Act: 2.3284. Min Act: -0.0000

Data Index: 26994 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 2.3284. Min Range: -2.3284

Max Act: 2.1960. Min Act: -0.0000

Data Index: 461847 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 2.3284. Min Range: -2.3284

Max Act: 2.2047. Min Act: -0.0000

Data Index: 283696 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 2.3284. Min Range: -2.3284

Max Act: 2.2697. Min Act: -0.0000

Data Index: 1309181 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 2.3284. Min Range: -2.3284

Max Act: 2.0546. Min Act: -0.0000

Data Index: 372062 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 2.3284. Min Range: -2.3284

Max Act: 2.0302. Min Act: -0.0000

Data Index: 1223668 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.9640. Min Act: -0.0000

Data Index: 1129473 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.7666. Min Act: -0.0000

Data Index: 24617 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.8441. Min Act: 0.0001

Data Index: 201504 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.6378. Min Act: -0.0000

Data Index: 899277 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.7005. Min Act: -0.0000

Data Index: 84755 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.6809. Min Act: -0.0000

Data Index: 516169 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.6657. Min Act: -0.0000

Data Index: 479913 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.6608. Min Act: -0.0000

Data Index: 418352 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.6401. Min Act: -0.0000

Data Index: 244795 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.5298. Min Act: -0.0000

Data Index: 504858 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1341379 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1154421 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.5309. Min Act: -0.0000

Data Index: 845950 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 2.3284. Min Range: -2.3284

Max Act: 1.4623. Min Act: -0.0000

Data Index: 644591 (C4 (Web Text))

Max Activating Token Index: 362