Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2550 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0941. Min Act: -0.0001

Data Index: 264030 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0969. Min Act: -0.0001

Data Index: 278086 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0855. Min Act: -0.0001

Data Index: 966699 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0900. Min Act: -0.0001

Data Index: 440561 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0873. Min Act: -0.0001

Data Index: 300503 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0835. Min Act: -0.0001

Data Index: 176259 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0845. Min Act: -0.0001

Data Index: 885993 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0848. Min Act: -0.0001

Data Index: 750717 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0779. Min Act: -0.0001

Data Index: 536019 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1291230 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0752. Min Act: -0.0001

Data Index: 454903 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0801. Min Act: -0.0001

Data Index: 223813 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0794. Min Act: -0.0001

Data Index: 493920 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0779. Min Act: -0.0001

Data Index: 768682 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1197702 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1103121 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0814. Min Act: -0.0001

Data Index: 757096 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0755. Min Act: -0.0001

Data Index: 740131 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0751. Min Act: -0.0001

Data Index: 900578 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0745. Min Act: -0.0001

Data Index: 163277 (C4 (Web Text))

Max Activating Token Index: 104