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

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

Neuron 8 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.7082. Min Act: -0.0001

Data Index: 838922 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5498. Min Act: -0.0000

Data Index: 697839 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4385. Min Act: -0.0001

Data Index: 972854 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1306446 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1319684 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4073. Min Act: -0.0000

Data Index: 709102 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4035. Min Act: -0.0000

Data Index: 165771 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1312467 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4190. Min Act: -0.0000

Data Index: 205965 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3914. Min Act: -0.0000

Data Index: 314096 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3876. Min Act: -0.0000

Data Index: 576898 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1126653 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3720. Min Act: -0.0000

Data Index: 191085 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1150204 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3691. Min Act: -0.0001

Data Index: 914375 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3684. Min Act: -0.0001

Data Index: 966748 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3696. Min Act: -0.0001

Data Index: 919032 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3688. Min Act: -0.0001

Data Index: 1053366 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3596. Min Act: -0.0000

Data Index: 782312 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.3544. Min Act: -0.0000

Data Index: 874363 (C4 (Web Text))

Max Activating Token Index: 870