Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2435 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.1849. Min Act: -0.0000

Data Index: 605557 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.1001. Min Act: -0.0000

Data Index: 907476 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9373. Min Act: -0.0001

Data Index: 790269 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9792. Min Act: -0.0001

Data Index: 249708 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9229. Min Act: -0.0001

Data Index: 288820 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8894. Min Act: -0.0000

Data Index: 980365 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8563. Min Act: -0.0000

Data Index: 712174 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8798. Min Act: -0.0000

Data Index: 437377 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8294. Min Act: -0.0001

Data Index: 1006517 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1253070 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1158404 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8019. Min Act: -0.0001

Data Index: 1118117 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8478. Min Act: -0.0000

Data Index: 760223 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8535. Min Act: -0.0000

Data Index: 879421 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1280713 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8398. Min Act: -0.0000

Data Index: 730242 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8452. Min Act: -0.0001

Data Index: 81843 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8405. Min Act: -0.0001

Data Index: 348300 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8081. Min Act: -0.0000

Data Index: 338544 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8341. Min Act: -0.0001

Data Index: 46491 (C4 (Web Text))

Max Activating Token Index: 176