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

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

Neuron 3172 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: 1.3121. Min Range: -1.3121

Max Act: 1.3121. Min Act: -0.0000

Data Index: 166024 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.3121. Min Range: -1.3121

Max Act: 1.0951. Min Act: -0.0000

Data Index: 536743 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.3121. Min Range: -1.3121

Max Act: 1.1059. Min Act: -0.0000

Data Index: 155728 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 1.3121. Min Range: -1.3121

Max Act: 1.0099. Min Act: -0.0001

Data Index: 818336 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.3121. Min Range: -1.3121

Max Act: 1.0646. Min Act: -0.0000

Data Index: 685235 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9786. Min Act: -0.0001

Data Index: 870713 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9450. Min Act: -0.0000

Data Index: 181656 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9717. Min Act: -0.0000

Data Index: 444054 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1146086 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9966. Min Act: -0.0000

Data Index: 313046 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9217. Min Act: -0.0000

Data Index: 551748 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9724. Min Act: -0.0000

Data Index: 514426 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1036653 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9432. Min Act: -0.0000

Data Index: 943331 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9402. Min Act: -0.0000

Data Index: 798220 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8944. Min Act: -0.0000

Data Index: 957047 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9009. Min Act: -0.0001

Data Index: 257883 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8713. Min Act: -0.0000

Data Index: 924357 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1514 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8915. Min Act: -0.0000

Data Index: 453117 (C4 (Web Text))

Max Activating Token Index: 470