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

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

Neuron 224 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8789. Min Act: -0.0000

Data Index: 678967 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8339. Min Act: -0.0000

Data Index: 905093 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1320046 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1005614 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8932. Min Act: -0.0000

Data Index: 789961 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1321010 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7938. Min Act: -0.0000

Data Index: 700867 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8931. Min Act: -0.0000

Data Index: 507943 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1357241 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7889. Min Act: -0.0000

Data Index: 117252 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7875. Min Act: -0.0000

Data Index: 622699 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8081. Min Act: -0.0000

Data Index: 460538 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7784. Min Act: -0.0000

Data Index: 304596 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1181441 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7611. Min Act: -0.0000

Data Index: 136486 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7863. Min Act: -0.0000

Data Index: 677378 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7595. Min Act: -0.0000

Data Index: 589777 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7599. Min Act: -0.0000

Data Index: 968402 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7769. Min Act: -0.0000

Data Index: 10589 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7525. Min Act: -0.0000

Data Index: 480180 (C4 (Web Text))

Max Activating Token Index: 421