Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 965 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1422053 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1132. Min Act: -0.0000

Data Index: 371293 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1094. Min Act: -0.0000

Data Index: 974619 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1090. Min Act: -0.0000

Data Index: 716594 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0890. Min Act: -0.0000

Data Index: 393279 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0997. Min Act: -0.0000

Data Index: 486879 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0906. Min Act: -0.0000

Data Index: 728123 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1040491 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1600081 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0943. Min Act: -0.0000

Data Index: 991938 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1455364 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1222643 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0893. Min Act: -0.0000

Data Index: 807060 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0737. Min Act: -0.0000

Data Index: 499505 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1399752 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0725. Min Act: -0.0000

Data Index: 440340 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1410719 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0750. Min Act: -0.0000

Data Index: 484578 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1525471 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1327146 (C4 (Web Text))

Max Activating Token Index: 569