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

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

Neuron 4126 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1603797 (Python Code)

Max Activating Token Index: 320

Text #1

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.3839. Min Act: -0.0000

Data Index: 88245 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.4735. Min Act: -0.0000

Data Index: 1411082 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1621699 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1457341 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.1894. Min Act: -0.0000

Data Index: 1621803 (Python Code)

Max Activating Token Index: 287

Text #6

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1336944 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.3119. Min Act: -0.0000

Data Index: 813284 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1508856 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.2094. Min Act: -0.0000

Data Index: 83390 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.2321. Min Act: -0.0000

Data Index: 940302 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1571686 (Python Code)

Max Activating Token Index: 926

Text #12

Max Range: 1.6253. Min Range: -1.6253

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1404482 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.1307. Min Act: -0.0000

Data Index: 18599 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1656845 (Python Code)

Max Activating Token Index: 886

Text #15

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.0887. Min Act: -0.0000

Data Index: 754676 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.0470. Min Act: -0.0000

Data Index: 174065 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1326166 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.6253. Min Range: -1.6253

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1482053 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 1.6253. Min Range: -1.6253

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1400637 (Python Code)

Max Activating Token Index: 290