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

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

Neuron 1154 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1752. Min Range: -1.1752

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1291786 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.1752. Min Range: -1.1752

Max Act: 1.0049. Min Act: -0.0000

Data Index: 993590 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 1.1752. Min Range: -1.1752

Max Act: 1.0377. Min Act: -0.0000

Data Index: 496294 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8869. Min Act: -0.0000

Data Index: 384417 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1260772 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1185141 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1241799 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8339. Min Act: -0.0000

Data Index: 551914 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1212276 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7944. Min Act: -0.0000

Data Index: 465412 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7562. Min Act: -0.0000

Data Index: 746476 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7502. Min Act: -0.0000

Data Index: 362358 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7553. Min Act: -0.0000

Data Index: 572308 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7475. Min Act: -0.0000

Data Index: 408887 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7472. Min Act: -0.0000

Data Index: 655599 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7250. Min Act: -0.0000

Data Index: 992819 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7468. Min Act: -0.0000

Data Index: 881913 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1245251 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7323. Min Act: -0.0000

Data Index: 213548 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7247. Min Act: -0.0000

Data Index: 513876 (C4 (Web Text))

Max Activating Token Index: 30