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

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

Neuron 2436 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.5883. Min Act: -0.0002

Data Index: 249435 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.5016. Min Act: -0.0002

Data Index: 947794 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.3314. Min Act: -0.0002

Data Index: 1068240 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.3350. Min Act: -0.0002

Data Index: 1041563 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.2882. Min Act: -0.0002

Data Index: 1163603 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.3488. Min Act: -0.0002

Data Index: 709930 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.1999. Min Act: -0.0002

Data Index: 624075 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.2408. Min Act: -0.0002

Data Index: 224430 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.2448. Min Act: -0.0002

Data Index: 481947 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.2245. Min Act: -0.0002

Data Index: 150270 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.2023. Min Act: -0.0002

Data Index: 71858 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.0880. Min Act: -0.0002

Data Index: 828511 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.2160. Min Act: -0.0002

Data Index: 404222 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.0964. Min Act: -0.0002

Data Index: 1225275 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.1623. Min Act: -0.0002

Data Index: 992456 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.1404. Min Act: -0.0002

Data Index: 38149 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.1684. Min Act: -0.0002

Data Index: 48828 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.1699. Min Act: -0.0002

Data Index: 993114 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.1721. Min Act: -0.0002

Data Index: 112858 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.5883. Min Range: -1.5883

Max Act: 1.1453. Min Act: -0.0002

Data Index: 62550 (C4 (Web Text))

Max Activating Token Index: 7