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

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

Neuron 3295 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0235. Min Range: -1.0235

Max Act: 1.0235. Min Act: -0.0001

Data Index: 1102372 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.0235. Min Range: -1.0235

Max Act: 1.0051. Min Act: -0.0001

Data Index: 649107 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.0235. Min Range: -1.0235

Max Act: 1.0108. Min Act: -0.0000

Data Index: 704828 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1005062 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9430. Min Act: -0.0001

Data Index: 56212 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9301. Min Act: -0.0001

Data Index: 454117 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8569. Min Act: -0.0001

Data Index: 276280 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9013. Min Act: -0.0001

Data Index: 129424 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8608. Min Act: -0.0001

Data Index: 766388 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1306719 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8773. Min Act: -0.0001

Data Index: 1183513 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8211. Min Act: -0.0001

Data Index: 552873 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1209432 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1084260 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8001. Min Act: -0.0001

Data Index: 458081 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8500. Min Act: -0.0001

Data Index: 984554 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8162. Min Act: -0.0001

Data Index: 166602 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7947. Min Act: -0.0001

Data Index: 84707 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8052. Min Act: -0.0001

Data Index: 872764 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8083. Min Act: -0.0001

Data Index: 1131165 (C4 (Web Text))

Max Activating Token Index: 904