Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2123 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6458. Min Act: -0.0004

Data Index: 1386715 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6172. Min Act: -0.0003

Data Index: 1645585 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5833. Min Act: -0.0003

Data Index: 1414250 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5399. Min Act: -0.0003

Data Index: 1453750 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5178. Min Act: -0.0003

Data Index: 1386593 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5890. Min Act: -0.0003

Data Index: 1640673 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5259. Min Act: -0.0003

Data Index: 1597085 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5065. Min Act: -0.0003

Data Index: 1564007 (Python Code)

Max Activating Token Index: 362

Text #8

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5444. Min Act: -0.0003

Data Index: 1455195 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5102. Min Act: -0.0003

Data Index: 1541454 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5081. Min Act: -0.0003

Data Index: 1654918 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5244. Min Act: -0.0003

Data Index: 1598719 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5094. Min Act: -0.0003

Data Index: 1422256 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5588. Min Act: -0.0003

Data Index: 1620677 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5009. Min Act: -0.0003

Data Index: 1607702 (Python Code)

Max Activating Token Index: 303

Text #15

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4669. Min Act: -0.0003

Data Index: 1456568 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5550. Min Act: -0.0003

Data Index: 1570994 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5019. Min Act: -0.0003

Data Index: 1651629 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4995. Min Act: -0.0003

Data Index: 1443157 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4957. Min Act: -0.0003

Data Index: 1611078 (Python Code)

Max Activating Token Index: 543