Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3146 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.5724. Min Range: -4.5724

Max Act: 4.2099. Min Act: -0.0000

Data Index: 706248 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 4.5724. Min Range: -4.5724

Max Act: 4.5724. Min Act: -0.0000

Data Index: 419126 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 4.5724. Min Range: -4.5724

Max Act: 3.8907. Min Act: -0.0000

Data Index: 1351493 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 4.5724. Min Range: -4.5724

Max Act: 3.5095. Min Act: -0.0000

Data Index: 1333383 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 4.5724. Min Range: -4.5724

Max Act: 3.6060. Min Act: -0.0000

Data Index: 1213843 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 4.5724. Min Range: -4.5724

Max Act: 3.0043. Min Act: -0.0000

Data Index: 176632 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 4.5724. Min Range: -4.5724

Max Act: 3.0004. Min Act: -0.0000

Data Index: 957742 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.8070. Min Act: -0.0000

Data Index: 1262069 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.6232. Min Act: -0.0000

Data Index: 1008134 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.6023. Min Act: -0.0000

Data Index: 515915 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.3974. Min Act: -0.0000

Data Index: 38358 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.4649. Min Act: -0.0000

Data Index: 179347 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.6060. Min Act: -0.0000

Data Index: 417931 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.3153. Min Act: -0.0000

Data Index: 85763 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.5746. Min Act: -0.0000

Data Index: 1530146 (Python Code)

Max Activating Token Index: 816

Text #15

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.2463. Min Act: -0.0000

Data Index: 400850 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.6985. Min Act: -0.0000

Data Index: 1249023 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.1814. Min Act: -0.0000

Data Index: 146445 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.2232. Min Act: -0.0000

Data Index: 449919 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 4.5724. Min Range: -4.5724

Max Act: 2.0445. Min Act: -0.0000

Data Index: 1597461 (Python Code)

Max Activating Token Index: 413