Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1434. Min Act: -0.0002

Data Index: 1304978 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1364. Min Act: -0.0002

Data Index: 475897 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1309415 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1176. Min Act: -0.0002

Data Index: 738350 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1204. Min Act: -0.0002

Data Index: 699436 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1216. Min Act: -0.0002

Data Index: 97023 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1169. Min Act: -0.0002

Data Index: 676600 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1234201 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1115. Min Act: -0.0002

Data Index: 507503 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1152. Min Act: -0.0002

Data Index: 87906 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1110. Min Act: -0.0002

Data Index: 756865 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1128. Min Act: -0.0002

Data Index: 321034 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1091. Min Act: -0.0002

Data Index: 162421 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1127. Min Act: -0.0002

Data Index: 276189 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1329751 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1079. Min Act: -0.0002

Data Index: 496374 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1060. Min Act: -0.0002

Data Index: 226132 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1218180 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1052. Min Act: -0.0002

Data Index: 675542 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1068. Min Act: -0.0002

Data Index: 724641 (C4 (Web Text))

Max Activating Token Index: 768