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

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

Neuron 5274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3806. Min Act: -0.0002

Data Index: 937248 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3301. Min Act: -0.0001

Data Index: 81266 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2974. Min Act: -0.0001

Data Index: 994131 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2116. Min Act: -0.0001

Data Index: 620972 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1115246 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1231176 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1924. Min Act: -0.0001

Data Index: 7065 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1913. Min Act: -0.0001

Data Index: 125673 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1815. Min Act: -0.0001

Data Index: 783086 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1739. Min Act: -0.0001

Data Index: 535458 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1356141 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1621. Min Act: -0.0001

Data Index: 288060 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1648. Min Act: -0.0001

Data Index: 840485 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1637. Min Act: -0.0001

Data Index: 640530 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1687. Min Act: -0.0001

Data Index: 35108 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1741. Min Act: -0.0001

Data Index: 526538 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1629. Min Act: -0.0002

Data Index: 1310970 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1746. Min Act: -0.0001

Data Index: 339192 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1035585 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.1661. Min Act: -0.0001

Data Index: 37805 (C4 (Web Text))

Max Activating Token Index: 277