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

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

Neuron 4284 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1485579 (Python Code)

Max Activating Token Index: 707

Text #1

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7297. Min Act: -0.0001

Data Index: 1545978 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1501327 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1625831 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7612. Min Act: -0.0001

Data Index: 1422891 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1510548 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7553. Min Act: -0.0001

Data Index: 1608207 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1597820 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1366176 (Python Code)

Max Activating Token Index: 875

Text #9

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1567560 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1610668 (Python Code)

Max Activating Token Index: 245

Text #11

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7151. Min Act: -0.0001

Data Index: 1468856 (Python Code)

Max Activating Token Index: 563

Text #12

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7523. Min Act: -0.0001

Data Index: 1470045 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1360692 (Python Code)

Max Activating Token Index: 866

Text #14

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1585964 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1449444 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1489939 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1372784 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1470331 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1429376 (Python Code)

Max Activating Token Index: 323