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

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

Neuron 1296 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: 2.0901. Min Range: -2.0901

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1520080 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.7924. Min Act: -0.0000

Data Index: 1389782 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1477751 (Python Code)

Max Activating Token Index: 598

Text #3

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.7694. Min Act: -0.0000

Data Index: 1552073 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1559616 (Python Code)

Max Activating Token Index: 119

Text #5

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.7662. Min Act: -0.0000

Data Index: 110055 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.7536. Min Act: -0.0000

Data Index: 340731 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1524413 (Python Code)

Max Activating Token Index: 1013

Text #8

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1237437 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.6176. Min Act: -0.0000

Data Index: 390020 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1656133 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5903. Min Act: -0.0000

Data Index: 286465 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5864. Min Act: -0.0000

Data Index: 748640 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.6083. Min Act: -0.0000

Data Index: 1628932 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1484066 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5548. Min Act: -0.0000

Data Index: 495880 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5736. Min Act: -0.0000

Data Index: 1536513 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5668. Min Act: -0.0000

Data Index: 1441495 (Python Code)

Max Activating Token Index: 475

Text #18

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1197543 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 2.0901. Min Range: -2.0901

Max Act: 1.5515. Min Act: -0.0000

Data Index: 1373377 (Python Code)

Max Activating Token Index: 948