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

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

Neuron 2784 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: 0.1140. Min Range: -0.1140

Max Act: 0.1098. Min Act: 0.0000

Data Index: 776429 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0000

Data Index: 400115 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1581558 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1235995 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0956. Min Act: -0.0000

Data Index: 726763 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0990. Min Act: 0.0000

Data Index: 610389 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1085187 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0974. Min Act: -0.0000

Data Index: 73821 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1262331 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0960. Min Act: -0.0000

Data Index: 250309 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0888. Min Act: -0.0000

Data Index: 535855 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0909. Min Act: -0.0000

Data Index: 529329 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1242875 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1071719 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1494802 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0823. Min Act: -0.0000

Data Index: 602929 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0835. Min Act: -0.0000

Data Index: 649125 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1265621 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0853. Min Act: -0.0000

Data Index: 703721 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0852. Min Act: -0.0000

Data Index: 40984 (C4 (Web Text))

Max Activating Token Index: 202