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

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

Neuron 1427 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1322. Min Act: -0.0001

Data Index: 891399 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1033096 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1453. Min Act: -0.0001

Data Index: 501533 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1678. Min Act: -0.0001

Data Index: 16154 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1259577 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1141958 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1539. Min Act: -0.0001

Data Index: 294985 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1562. Min Act: -0.0001

Data Index: 939749 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1618. Min Act: -0.0001

Data Index: 227795 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1718. Min Act: -0.0001

Data Index: 259036 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1226083 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1475. Min Act: -0.0001

Data Index: 754653 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1459. Min Act: -0.0001

Data Index: 104946 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1352. Min Act: -0.0001

Data Index: 152362 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1427. Min Act: -0.0001

Data Index: 303785 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1430. Min Act: -0.0001

Data Index: 341383 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1622. Min Act: -0.0001

Data Index: 361290 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1176067 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1139. Min Act: -0.0001

Data Index: 8164 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1437. Min Act: -0.0001

Data Index: 641768 (C4 (Web Text))

Max Activating Token Index: 573