Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 135 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.6002. Min Act: -0.0001

Data Index: 131838 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.4960. Min Act: -0.0000

Data Index: 80186 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.4380. Min Act: -0.0000

Data Index: 691213 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.4119. Min Act: -0.0000

Data Index: 312324 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.3417. Min Act: -0.0000

Data Index: 824811 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.3648. Min Act: -0.0000

Data Index: 977077 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.3039. Min Act: -0.0000

Data Index: 813701 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.3806. Min Act: -0.0000

Data Index: 43729 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.3118. Min Act: -0.0000

Data Index: 549603 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1836. Min Act: -0.0001

Data Index: 1071657 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2596. Min Act: -0.0000

Data Index: 589592 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2939. Min Act: -0.0000

Data Index: 768679 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1495. Min Act: -0.0000

Data Index: 330955 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2125. Min Act: -0.0000

Data Index: 198692 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2806. Min Act: -0.0000

Data Index: 893015 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2091. Min Act: -0.0000

Data Index: 713530 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2379. Min Act: -0.0000

Data Index: 789651 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1889. Min Act: -0.0000

Data Index: 450817 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1787. Min Act: -0.0001

Data Index: 550112 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1057026 (C4 (Web Text))

Max Activating Token Index: 963