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

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

Neuron 4162 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.7649. Min Act: -0.0000

Data Index: 744129 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.3172. Min Act: -0.0000

Data Index: 393663 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.6978. Min Act: -0.0000

Data Index: 686102 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.8386. Min Act: -0.0000

Data Index: 1118588 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.8521. Min Act: -0.0000

Data Index: 545319 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 4.7649. Min Range: -4.7649

Max Act: 4.1115. Min Act: -0.0000

Data Index: 1147850 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.5732. Min Act: -0.0000

Data Index: 452884 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.7302. Min Act: -0.0000

Data Index: 468787 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.7063. Min Act: -0.0000

Data Index: 38141 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.7219. Min Act: -0.0000

Data Index: 1291778 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.8491. Min Act: -0.0000

Data Index: 1062765 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.5800. Min Act: -0.0000

Data Index: 316233 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.5496. Min Act: -0.0000

Data Index: 544735 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.4683. Min Act: -0.0000

Data Index: 555748 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.3972. Min Act: -0.0000

Data Index: 1173104 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.3648. Min Act: -0.0000

Data Index: 274691 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.1780. Min Act: -0.0000

Data Index: 357397 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.3320. Min Act: -0.0000

Data Index: 1213179 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.3361. Min Act: -0.0000

Data Index: 534371 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 4.7649. Min Range: -4.7649

Max Act: 3.4234. Min Act: -0.0000

Data Index: 1231738 (C4 (Web Text))

Max Activating Token Index: 954