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

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

Neuron 3692 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3718. Min Range: -1.3718

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1291743 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.3718. Min Range: -1.3718

Max Act: 1.0819. Min Act: -0.0000

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.8525. Min Act: -0.0000

Data Index: 126914 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.3718. Min Range: -1.3718

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1241305 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.3718. Min Range: -1.3718

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1048598 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.8487. Min Act: -0.0000

Data Index: 473623 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.7197. Min Act: -0.0000

Data Index: 882953 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1215979 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.6619. Min Act: -0.0000

Data Index: 702365 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.6301. Min Act: -0.0000

Data Index: 371751 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.7556. Min Act: -0.0000

Data Index: 965215 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1241488 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1306840 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1130419 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.5806. Min Act: -0.0000

Data Index: 767612 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.5252. Min Act: -0.0000

Data Index: 124419 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1656717 (Python Code)

Max Activating Token Index: 910

Text #17

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1220221 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.4100. Min Act: -0.0000

Data Index: 781796 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.3718. Min Range: -1.3718

Max Act: 0.4141. Min Act: -0.0000

Data Index: 510634 (C4 (Web Text))

Max Activating Token Index: 325