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

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

Neuron 3595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2823. Min Act: -0.0000

Data Index: 968498 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2680. Min Act: -0.0000

Data Index: 141467 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2545. Min Act: -0.0000

Data Index: 289556 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2602. Min Act: -0.0000

Data Index: 401887 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2481. Min Act: -0.0000

Data Index: 245578 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1047250 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1246132 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2163. Min Act: -0.0000

Data Index: 26799 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2102. Min Act: -0.0000

Data Index: 820436 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1167814 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2304. Min Act: -0.0000

Data Index: 922092 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1877. Min Act: -0.0000

Data Index: 321115 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1203680 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1903. Min Act: -0.0000

Data Index: 831774 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1062757 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1119195 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1239199 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1685. Min Act: -0.0000

Data Index: 312896 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1844. Min Act: -0.0000

Data Index: 777929 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1826. Min Act: -0.0000

Data Index: 143323 (C4 (Web Text))

Max Activating Token Index: 486