Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1930. Min Act: -0.0003

Data Index: 1295394 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1920. Min Act: -0.0003

Data Index: 1030896 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.2137. Min Act: -0.0003

Data Index: 477888 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.2041. Min Act: -0.0003

Data Index: 1092801 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.2154. Min Act: -0.0003

Data Index: 821044 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.2048. Min Act: -0.0003

Data Index: 354269 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1672. Min Act: -0.0003

Data Index: 237034 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1879. Min Act: -0.0003

Data Index: 954266 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1667. Min Act: -0.0003

Data Index: 830774 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1514. Min Act: -0.0003

Data Index: 1157013 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1869. Min Act: -0.0003

Data Index: 633396 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.2023. Min Act: -0.0003

Data Index: 1114809 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1916. Min Act: -0.0003

Data Index: 793398 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1758. Min Act: -0.0003

Data Index: 35132 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1893. Min Act: -0.0003

Data Index: 530428 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1740. Min Act: -0.0003

Data Index: 726092 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1618. Min Act: -0.0003

Data Index: 371097 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1942. Min Act: -0.0003

Data Index: 955818 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1583. Min Act: -0.0003

Data Index: 293703 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1726. Min Act: -0.0003

Data Index: 1046954 (C4 (Web Text))

Max Activating Token Index: 738