Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 930 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4796. Min Act: -0.0003

Data Index: 1487063 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3699. Min Act: -0.0003

Data Index: 1562887 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3400. Min Act: -0.0003

Data Index: 1624306 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.1611. Min Act: -0.0003

Data Index: 1477005 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.1967. Min Act: -0.0003

Data Index: 1476733 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.1825. Min Act: -0.0003

Data Index: 1422031 (Python Code)

Max Activating Token Index: 240

Text #6

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.1132. Min Act: -0.0003

Data Index: 1489187 (Python Code)

Max Activating Token Index: 736

Text #7

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0983. Min Act: -0.0003

Data Index: 1612059 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1418501 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0970. Min Act: -0.0003

Data Index: 1618847 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0981. Min Act: -0.0003

Data Index: 1366421 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1432379 (Python Code)

Max Activating Token Index: 436

Text #12

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0977. Min Act: -0.0003

Data Index: 1435010 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0943. Min Act: -0.0003

Data Index: 1442422 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1506870 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1421577 (Python Code)

Max Activating Token Index: 494

Text #16

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0901. Min Act: -0.0003

Data Index: 1470940 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0877. Min Act: -0.0004

Data Index: 1553900 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0851. Min Act: -0.0003

Data Index: 1481723 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1499428 (Python Code)

Max Activating Token Index: 434