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

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

Neuron 4661 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4486. Min Act: -0.0001

Data Index: 500298 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4423. Min Act: -0.0001

Data Index: 93739 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4526. Min Act: -0.0001

Data Index: 1164945 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4653. Min Act: -0.0001

Data Index: 1153997 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4693. Min Act: -0.0001

Data Index: 68986 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1244555 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4586. Min Act: -0.0001

Data Index: 527420 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4540. Min Act: -0.0001

Data Index: 720770 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4101. Min Act: -0.0001

Data Index: 255706 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4253. Min Act: -0.0001

Data Index: 770003 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4659. Min Act: -0.0001

Data Index: 625953 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4036. Min Act: -0.0001

Data Index: 450801 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4381. Min Act: -0.0001

Data Index: 846226 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4400. Min Act: -0.0001

Data Index: 920829 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4431. Min Act: -0.0001

Data Index: 816289 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4398. Min Act: -0.0001

Data Index: 296240 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4260. Min Act: -0.0001

Data Index: 1025527 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4076. Min Act: -0.0001

Data Index: 884218 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4174. Min Act: -0.0001

Data Index: 303052 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.4159. Min Act: -0.0001

Data Index: 709136 (C4 (Web Text))

Max Activating Token Index: 824