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

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

Neuron 657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5917. Min Act: -0.0000

Data Index: 974511 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5691. Min Act: -0.0000

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1298372 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1152874 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5642. Min Act: -0.0000

Data Index: 946786 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1088870 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5445. Min Act: -0.0000

Data Index: 115725 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5203. Min Act: -0.0000

Data Index: 377352 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5100. Min Act: -0.0000

Data Index: 28017 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4758. Min Act: -0.0000

Data Index: 804880 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5114. Min Act: -0.0000

Data Index: 720887 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4935. Min Act: -0.0000

Data Index: 760188 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5215. Min Act: -0.0000

Data Index: 836578 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1257517 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4756. Min Act: -0.0000

Data Index: 230231 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4374. Min Act: -0.0000

Data Index: 35346 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4788. Min Act: -0.0000

Data Index: 625264 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1196380 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1238890 (C4 (Web Text))

Max Activating Token Index: 898