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

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

Neuron 1494 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.2439. Min Act: -0.0000

Data Index: 727822 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1033001 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1332. Min Act: -0.0000

Data Index: 407935 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1165625 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9970. Min Act: -0.0000

Data Index: 577822 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0796. Min Act: -0.0000

Data Index: 370595 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1213. Min Act: -0.0000

Data Index: 938824 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1128. Min Act: -0.0000

Data Index: 329282 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1068. Min Act: -0.0000

Data Index: 974780 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9809. Min Act: -0.0000

Data Index: 558202 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0664. Min Act: -0.0000

Data Index: 102989 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1572228 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9251. Min Act: -0.0000

Data Index: 285972 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1060620 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1339785 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1515721 (Python Code)

Max Activating Token Index: 416

Text #16

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8029. Min Act: -0.0000

Data Index: 915813 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1214923 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8903. Min Act: -0.0000

Data Index: 952479 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8682. Min Act: -0.0000

Data Index: 859305 (C4 (Web Text))

Max Activating Token Index: 132