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

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

Neuron 791 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3733. Min Act: -0.0001

Data Index: 1576234 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3588. Min Act: -0.0001

Data Index: 1487408 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1540421 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3376. Min Act: -0.0001

Data Index: 1497510 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3460. Min Act: -0.0001

Data Index: 1576740 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3430. Min Act: -0.0001

Data Index: 1636441 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1566151 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1573211 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3439. Min Act: -0.0001

Data Index: 1647595 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1426566 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3302. Min Act: -0.0001

Data Index: 1514734 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3295. Min Act: -0.0001

Data Index: 1407459 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1464543 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1652072 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3198. Min Act: -0.0001

Data Index: 1567542 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3092. Min Act: -0.0001

Data Index: 1457769 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3128. Min Act: -0.0001

Data Index: 1636265 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1414761 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1424298 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3071. Min Act: -0.0001

Data Index: 1577917 (Python Code)

Max Activating Token Index: 19