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

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

Neuron 5050 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: 1.4526. Min Range: -1.4526

Max Act: 1.4432. Min Act: -0.0000

Data Index: 435477 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.4312. Min Act: -0.0000

Data Index: 131728 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.4526. Min Act: -0.0000

Data Index: 688205 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.4367. Min Act: -0.0000

Data Index: 223652 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1022473 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1112292 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.2909. Min Act: -0.0000

Data Index: 924928 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1758. Min Act: -0.0000

Data Index: 359050 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.2009. Min Act: -0.0000

Data Index: 650925 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1614. Min Act: -0.0000

Data Index: 259768 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1013061 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1296706 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.2587. Min Act: -0.0000

Data Index: 843717 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1517. Min Act: -0.0000

Data Index: 400215 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1691. Min Act: -0.0000

Data Index: 514529 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1566. Min Act: -0.0000

Data Index: 718735 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1157. Min Act: -0.0000

Data Index: 343815 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1331474 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1336. Min Act: -0.0000

Data Index: 740883 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.4526. Min Range: -1.4526

Max Act: 1.1637. Min Act: -0.0000

Data Index: 802825 (C4 (Web Text))

Max Activating Token Index: 670