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

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

Neuron 4220 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: 2.3451. Min Range: -2.3451

Max Act: 2.3451. Min Act: -0.0000

Data Index: 1122159 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.7517. Min Act: -0.0000

Data Index: 666409 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.6307. Min Act: -0.0000

Data Index: 352772 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.5783. Min Act: -0.0000

Data Index: 99201 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.5750. Min Act: -0.0000

Data Index: 1225081 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.4185. Min Act: -0.0000

Data Index: 408085 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1093878 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.4315. Min Act: -0.0000

Data Index: 35590 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.3373. Min Act: -0.0000

Data Index: 888964 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.2908. Min Act: -0.0000

Data Index: 12999 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.2816. Min Act: -0.0000

Data Index: 609582 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.1972. Min Act: -0.0000

Data Index: 298925 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.1853. Min Act: -0.0000

Data Index: 530807 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.1353. Min Act: -0.0000

Data Index: 884448 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.1759. Min Act: -0.0000

Data Index: 375147 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 2.3451. Min Range: -2.3451

Max Act: 1.0646. Min Act: -0.0000

Data Index: 432550 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 2.3451. Min Range: -2.3451

Max Act: 0.8615. Min Act: -0.0000

Data Index: 572679 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 2.3451. Min Range: -2.3451

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1155417 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 2.3451. Min Range: -2.3451

Max Act: 0.8383. Min Act: -0.0000

Data Index: 112851 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 2.3451. Min Range: -2.3451

Max Act: 0.8138. Min Act: -0.0000

Data Index: 566995 (C4 (Web Text))

Max Activating Token Index: 148