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

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

Neuron 2809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.2515. Min Act: -0.0000

Data Index: 864408 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9535. Min Act: -0.0000

Data Index: 916474 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8328. Min Act: -0.0000

Data Index: 273453 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8623. Min Act: -0.0000

Data Index: 61939 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1077580 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8406. Min Act: -0.0000

Data Index: 935406 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8799. Min Act: -0.0000

Data Index: 317263 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1230049 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8256. Min Act: -0.0000

Data Index: 742283 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8225. Min Act: -0.0000

Data Index: 85117 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7950. Min Act: -0.0000

Data Index: 746059 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1492796 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1512142 (Python Code)

Max Activating Token Index: 401

Text #13

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1031410 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1596907 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7012. Min Act: -0.0000

Data Index: 480105 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7938. Min Act: -0.0000

Data Index: 613381 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7693. Min Act: -0.0000

Data Index: 89378 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8078. Min Act: -0.0000

Data Index: 561896 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7551. Min Act: -0.0000

Data Index: 133853 (C4 (Web Text))

Max Activating Token Index: 239