Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4583 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6173. Min Act: -0.0000

Data Index: 946966 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6494. Min Act: -0.0000

Data Index: 541120 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6398. Min Act: -0.0001

Data Index: 8957 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5947. Min Act: -0.0000

Data Index: 853525 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6024. Min Act: -0.0000

Data Index: 343256 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5552. Min Act: -0.0001

Data Index: 850078 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1180935 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1066207 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1049005 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5415. Min Act: -0.0000

Data Index: 750190 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5206. Min Act: -0.0000

Data Index: 834284 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5314. Min Act: -0.0000

Data Index: 670756 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5244. Min Act: -0.0000

Data Index: 896740 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4671. Min Act: -0.0000

Data Index: 943495 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1043220 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5051. Min Act: -0.0000

Data Index: 378649 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1031177 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5105. Min Act: -0.0000

Data Index: 630433 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5010. Min Act: -0.0000

Data Index: 461976 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5089. Min Act: -0.0000

Data Index: 559635 (C4 (Web Text))

Max Activating Token Index: 304