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

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

Neuron 3508 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0330. Min Act: -0.0000

Data Index: 234651 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1099309 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0486. Min Act: -0.0000

Data Index: 318441 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0031. Min Act: -0.0000

Data Index: 99855 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1222792 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8879. Min Act: -0.0000

Data Index: 608483 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9709. Min Act: -0.0000

Data Index: 984177 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8829. Min Act: 0.0000

Data Index: 1314864 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8178. Min Act: -0.0000

Data Index: 178594 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1358173 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8138. Min Act: 0.0000

Data Index: 140868 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8710. Min Act: -0.0000

Data Index: 697823 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.7905. Min Act: -0.0000

Data Index: 85511 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8039. Min Act: -0.0000

Data Index: 718668 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.8020. Min Act: -0.0000

Data Index: 654084 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.7521. Min Act: -0.0000

Data Index: 617857 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1276791 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.7195. Min Act: -0.0000

Data Index: 677417 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1221655 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.7503. Min Act: -0.0000

Data Index: 796926 (C4 (Web Text))

Max Activating Token Index: 615