Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3058 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1441076 (Python Code)

Max Activating Token Index: 813

Text #1

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1563816 (Python Code)

Max Activating Token Index: 923

Text #2

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1985. Min Act: -0.0001

Data Index: 1628408 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1654107 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1431494 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1430959 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1655484 (Python Code)

Max Activating Token Index: 949

Text #7

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1398232 (Python Code)

Max Activating Token Index: 892

Text #8

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1712. Min Act: -0.0001

Data Index: 1555541 (Python Code)

Max Activating Token Index: 855

Text #9

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1642975 (Python Code)

Max Activating Token Index: 930

Text #10

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1396322 (Python Code)

Max Activating Token Index: 843

Text #11

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1544091 (Python Code)

Max Activating Token Index: 900

Text #12

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1513393 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2007. Min Act: -0.0001

Data Index: 1595956 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1551968 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1957. Min Act: -0.0001

Data Index: 1617068 (Python Code)

Max Activating Token Index: 942

Text #16

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1573289 (Python Code)

Max Activating Token Index: 818

Text #17

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1449779 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1500665 (Python Code)

Max Activating Token Index: 984

Text #19

Max Range: 0.2319. Min Range: -0.2319

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1505945 (Python Code)

Max Activating Token Index: 986