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

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

Neuron 2972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.6305. Min Act: -0.0000

Data Index: 370422 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.3798. Min Act: -0.0000

Data Index: 646565 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.3305. Min Act: -0.0000

Data Index: 309660 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 3.6305. Min Range: -3.6305

Max Act: 3.1975. Min Act: -0.0000

Data Index: 1084110 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.9122. Min Act: -0.0000

Data Index: 194782 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.7468. Min Act: -0.0000

Data Index: 1122629 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.6707. Min Act: -0.0000

Data Index: 749232 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.4446. Min Act: -0.0000

Data Index: 809475 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.5152. Min Act: -0.0000

Data Index: 680169 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.5055. Min Act: -0.0000

Data Index: 627536 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.3534. Min Act: -0.0000

Data Index: 802091 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.1982. Min Act: -0.0000

Data Index: 442181 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.1872. Min Act: -0.0000

Data Index: 950534 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.2139. Min Act: -0.0000

Data Index: 181088 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 3.6305. Min Range: -3.6305

Max Act: 2.0821. Min Act: -0.0000

Data Index: 1327237 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.6305. Min Range: -3.6305

Max Act: 1.9399. Min Act: -0.0000

Data Index: 385375 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 3.6305. Min Range: -3.6305

Max Act: 1.8855. Min Act: -0.0000

Data Index: 1318139 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 3.6305. Min Range: -3.6305

Max Act: 1.8408. Min Act: -0.0000

Data Index: 877392 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 3.6305. Min Range: -3.6305

Max Act: 1.7267. Min Act: -0.0000

Data Index: 4756 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 3.6305. Min Range: -3.6305

Max Act: 1.8129. Min Act: -0.0000

Data Index: 610654 (C4 (Web Text))

Max Activating Token Index: 554