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

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

Neuron 562 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2988. Min Range: -2.2988

Max Act: 2.2988. Min Act: -0.0000

Data Index: 20331 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.9127. Min Act: -0.0000

Data Index: 145039 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.9252. Min Act: -0.0000

Data Index: 22100 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 2.2988. Min Range: -2.2988

Max Act: 2.1295. Min Act: -0.0000

Data Index: 750004 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.7727. Min Act: -0.0000

Data Index: 536935 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.8728. Min Act: -0.0000

Data Index: 742913 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.7589. Min Act: -0.0000

Data Index: 83863 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.9615. Min Act: -0.0000

Data Index: 1069391 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.6445. Min Act: -0.0000

Data Index: 418903 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.2727. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.4004. Min Act: -0.0000

Data Index: 747867 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.3605. Min Act: -0.0000

Data Index: 898551 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1157908 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.3157. Min Act: -0.0000

Data Index: 587345 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.3114. Min Act: -0.0000

Data Index: 255470 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.2765. Min Act: -0.0000

Data Index: 1239632 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.3154. Min Act: -0.0000

Data Index: 906100 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.2057. Min Act: -0.0000

Data Index: 559201 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1193384 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 2.2988. Min Range: -2.2988

Max Act: 1.2095. Min Act: -0.0000

Data Index: 43761 (C4 (Web Text))

Max Activating Token Index: 245