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

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

Neuron 801 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0167. Min Act: -0.0001

Data Index: 246859 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0147. Min Act: -0.0001

Data Index: 612950 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0147. Min Act: -0.0001

Data Index: 512766 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0147. Min Act: -0.0001

Data Index: 685554 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0139. Min Act: -0.0001

Data Index: 49346 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0131. Min Act: -0.0001

Data Index: 739397 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0139. Min Act: -0.0001

Data Index: 421702 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0128. Min Act: -0.0001

Data Index: 472474 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0123. Min Act: -0.0001

Data Index: 953434 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0124. Min Act: -0.0001

Data Index: 178402 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0115. Min Act: -0.0001

Data Index: 15861 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1529935 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0119. Min Act: -0.0001

Data Index: 798760 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0099. Min Act: -0.0001

Data Index: 979579 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0112. Min Act: -0.0001

Data Index: 1166834 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0113. Min Act: -0.0001

Data Index: 312881 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0103. Min Act: -0.0001

Data Index: 193448 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0115. Min Act: -0.0001

Data Index: 915742 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0103. Min Act: -0.0001

Data Index: 383665 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0111. Min Act: -0.0001

Data Index: 1107398 (C4 (Web Text))

Max Activating Token Index: 190