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

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

Neuron 1200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1748. Min Act: -0.0001

Data Index: 985438 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0028. Min Act: -0.0000

Data Index: 681117 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9962. Min Act: -0.0000

Data Index: 65948 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1237671 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1010202 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1285531 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1174114 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8534. Min Act: -0.0000

Data Index: 405867 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8039. Min Act: -0.0001

Data Index: 374884 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1027454 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1074984 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8676. Min Act: -0.0001

Data Index: 765911 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8543. Min Act: -0.0000

Data Index: 65126 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8226. Min Act: -0.0001

Data Index: 915159 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1253009 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7889. Min Act: -0.0001

Data Index: 368870 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1079132 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8144. Min Act: -0.0000

Data Index: 143674 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7605. Min Act: -0.0000

Data Index: 317430 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1104854 (C4 (Web Text))

Max Activating Token Index: 483