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

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

Neuron 1808 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.2544. Min Act: -0.0000

Data Index: 248329 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.4574. Min Act: -0.0000

Data Index: 986527 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.3255. Min Act: -0.0000

Data Index: 318591 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.2988. Min Act: -0.0000

Data Index: 512612 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.0916. Min Act: -0.0000

Data Index: 1363459 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1007681 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 3.2544. Min Range: -3.2544

Max Act: 1.9737. Min Act: -0.0000

Data Index: 1273545 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.3593. Min Act: -0.0000

Data Index: 1110481 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.1078. Min Act: -0.0000

Data Index: 139004 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.2343. Min Act: -0.0000

Data Index: 1296672 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.0711. Min Act: -0.0000

Data Index: 266996 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.0941. Min Act: -0.0000

Data Index: 1334183 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.0477. Min Act: -0.0000

Data Index: 1067783 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.2406. Min Act: -0.0000

Data Index: 1152540 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.0157. Min Act: -0.0000

Data Index: 999835 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 3.2544. Min Range: -3.2544

Max Act: 2.0117. Min Act: -0.0000

Data Index: 810610 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 3.2544. Min Range: -3.2544

Max Act: 1.9800. Min Act: -0.0000

Data Index: 1315643 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 3.2544. Min Range: -3.2544

Max Act: 1.6517. Min Act: -0.0000

Data Index: 1501995 (Python Code)

Max Activating Token Index: 480

Text #18

Max Range: 3.2544. Min Range: -3.2544

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1260021 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.2544. Min Range: -3.2544

Max Act: 1.9546. Min Act: -0.0000

Data Index: 315437 (C4 (Web Text))

Max Activating Token Index: 799