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

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

Neuron 2556 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.6899. Min Act: -0.0000

Data Index: 1580481 (Python Code)

Max Activating Token Index: 991

Text #1

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.5014. Min Act: -0.0000

Data Index: 1626919 (Python Code)

Max Activating Token Index: 695

Text #2

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3455. Min Act: -0.0000

Data Index: 1420849 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.5039. Min Act: -0.0000

Data Index: 1556557 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.4148. Min Act: -0.0000

Data Index: 1397061 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1635353 (Python Code)

Max Activating Token Index: 536

Text #6

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1627940 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1430807 (Python Code)

Max Activating Token Index: 300

Text #8

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1379148 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1446450 (Python Code)

Max Activating Token Index: 357

Text #10

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1565465 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1476488 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.2775. Min Act: -0.0000

Data Index: 1523141 (Python Code)

Max Activating Token Index: 542

Text #13

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1527379 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.2201. Min Act: -0.0000

Data Index: 1371488 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1481191 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1500093 (Python Code)

Max Activating Token Index: 455

Text #17

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1436981 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1595278 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1471270 (Python Code)

Max Activating Token Index: 651