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

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

Neuron 5602 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.2112. Min Act: -0.0000

Data Index: 730460 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.3917. Min Act: -0.0000

Data Index: 722621 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 4.3917. Min Range: -4.3917

Max Act: 3.6126. Min Act: -0.0000

Data Index: 528613 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 4.3917. Min Range: -4.3917

Max Act: 3.2491. Min Act: -0.0000

Data Index: 942663 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 4.3917. Min Range: -4.3917

Max Act: 3.1352. Min Act: -0.0000

Data Index: 316135 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.9330. Min Act: -0.0000

Data Index: 22936 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 4.3917. Min Range: -4.3917

Max Act: 3.0806. Min Act: -0.0000

Data Index: 1184187 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 4.3917. Min Range: -4.3917

Max Act: 3.0650. Min Act: -0.0000

Data Index: 627880 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.8424. Min Act: -0.0000

Data Index: 1173733 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.8242. Min Act: -0.0000

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.7904. Min Act: -0.0000

Data Index: 1284141 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.7970. Min Act: -0.0000

Data Index: 135244 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.6391. Min Act: -0.0000

Data Index: 899625 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.4920. Min Act: -0.0000

Data Index: 459305 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.5743. Min Act: -0.0000

Data Index: 142411 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.5154. Min Act: -0.0000

Data Index: 237284 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.6565. Min Act: -0.0000

Data Index: 908665 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.6069. Min Act: -0.0000

Data Index: 565726 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.4709. Min Act: -0.0000

Data Index: 1331649 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 4.3917. Min Range: -4.3917

Max Act: 2.3486. Min Act: -0.0000

Data Index: 661748 (C4 (Web Text))

Max Activating Token Index: 376