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

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

Neuron 3757 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: 4.2570. Min Range: -4.2570

Max Act: 4.2570. Min Act: -0.0000

Data Index: 244775 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.9867. Min Act: -0.0000

Data Index: 419797 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.7573. Min Act: -0.0000

Data Index: 1585329 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.6505. Min Act: -0.0000

Data Index: 1542749 (Python Code)

Max Activating Token Index: 707

Text #4

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.6244. Min Act: -0.0000

Data Index: 874819 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.5564. Min Act: -0.0000

Data Index: 493741 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.6109. Min Act: -0.0000

Data Index: 775894 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.8857. Min Act: -0.0000

Data Index: 1155165 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.3915. Min Act: -0.0000

Data Index: 1058969 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.3130. Min Act: -0.0000

Data Index: 171322 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.2588. Min Act: -0.0000

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.2826. Min Act: -0.0000

Data Index: 884763 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.0496. Min Act: -0.0000

Data Index: 1433502 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.1242. Min Act: -0.0000

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 4.2570. Min Range: -4.2570

Max Act: 3.0499. Min Act: 0.0000

Data Index: 264795 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 4.2570. Min Range: -4.2570

Max Act: 2.9941. Min Act: -0.0000

Data Index: 803877 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 4.2570. Min Range: -4.2570

Max Act: 2.9801. Min Act: -0.0000

Data Index: 1351336 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 4.2570. Min Range: -4.2570

Max Act: 2.9031. Min Act: -0.0000

Data Index: 341246 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 4.2570. Min Range: -4.2570

Max Act: 2.8512. Min Act: -0.0000

Data Index: 745731 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 4.2570. Min Range: -4.2570

Max Act: 2.8301. Min Act: -0.0000

Data Index: 848222 (C4 (Web Text))

Max Activating Token Index: 947