Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.1725. Min Act: -0.0001

Data Index: 1551986 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.1552. Min Act: -0.0001

Data Index: 1639289 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9794. Min Act: -0.0001

Data Index: 1465031 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0460. Min Act: -0.0001

Data Index: 1471887 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0768. Min Act: -0.0001

Data Index: 1540856 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.7835. Min Act: -0.0001

Data Index: 1577538 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9833. Min Act: -0.0001

Data Index: 1446138 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9022. Min Act: -0.0001

Data Index: 1640323 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0169. Min Act: -0.0001

Data Index: 1471781 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9058. Min Act: -0.0001

Data Index: 1655897 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9260. Min Act: -0.0001

Data Index: 1415056 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9784. Min Act: -0.0001

Data Index: 1536460 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.5171. Min Act: -0.0001

Data Index: 1419365 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8326. Min Act: -0.0001

Data Index: 1448118 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9519. Min Act: -0.0001

Data Index: 1422831 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0539. Min Act: -0.0001

Data Index: 1601096 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9165. Min Act: -0.0001

Data Index: 1570813 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8153. Min Act: -0.0001

Data Index: 1556884 (Python Code)

Max Activating Token Index: 927

Text #18

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8472. Min Act: -0.0001

Data Index: 1414858 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.7635. Min Act: -0.0001

Data Index: 1394500 (Python Code)

Max Activating Token Index: 224