Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2760 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1377924 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1560139 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1153013 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1498430 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1585307 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0849. Min Act: -0.0002

Data Index: 554992 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1036289 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1563077 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1036050 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0797. Min Act: -0.0002

Data Index: 612252 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1364582 (Python Code)

Max Activating Token Index: 332

Text #11

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1379608 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1457831 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1413541 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1545724 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1363055 (Python Code)

Max Activating Token Index: 885

Text #16

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1191467 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1539210 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1626220 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1601456 (Python Code)

Max Activating Token Index: 540