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

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

Neuron 4063 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.8353. Min Act: -0.0000

Data Index: 350830 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.9029. Min Act: -0.0000

Data Index: 280683 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.7719. Min Act: -0.0000

Data Index: 1045556 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.6176. Min Act: -0.0000

Data Index: 448801 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.5256. Min Act: -0.0000

Data Index: 667844 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.4221. Min Act: -0.0000

Data Index: 572512 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.4127. Min Act: -0.0000

Data Index: 706460 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.2716. Min Act: -0.0000

Data Index: 1634141 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.2457. Min Act: -0.0000

Data Index: 1536971 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.0956. Min Act: -0.0000

Data Index: 511144 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1363868 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1490309 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9282. Min Act: -0.0000

Data Index: 314164 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.9029. Min Range: -1.9029

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1636351 (Python Code)

Max Activating Token Index: 162

Text #14

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1584661 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9758. Min Act: -0.0000

Data Index: 527915 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1514685 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1587866 (Python Code)

Max Activating Token Index: 677

Text #18

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9718. Min Act: -0.0000

Data Index: 729210 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.9029. Min Range: -1.9029

Max Act: 0.9373. Min Act: -0.0000

Data Index: 287738 (C4 (Web Text))

Max Activating Token Index: 409