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

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

Neuron 3993 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0290. Min Range: -2.0290

Max Act: 2.0290. Min Act: -0.0000

Data Index: 1594131 (Python Code)

Max Activating Token Index: 561

Text #1

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.9752. Min Act: -0.0000

Data Index: 1442226 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.9726. Min Act: -0.0000

Data Index: 1582251 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.6539. Min Act: -0.0000

Data Index: 1378711 (Python Code)

Max Activating Token Index: 213

Text #4

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1510959 (Python Code)

Max Activating Token Index: 900

Text #5

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.5250. Min Act: -0.0000

Data Index: 1613864 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.4841. Min Act: -0.0000

Data Index: 1429546 (Python Code)

Max Activating Token Index: 219

Text #7

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1482661 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1561483 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.4482. Min Act: -0.0000

Data Index: 1467366 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1632189 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1492318 (Python Code)

Max Activating Token Index: 933

Text #12

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1542828 (Python Code)

Max Activating Token Index: 470

Text #13

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1625724 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1588738 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1495113 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1627028 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1467720 (Python Code)

Max Activating Token Index: 884

Text #18

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1398527 (Python Code)

Max Activating Token Index: 218

Text #19

Max Range: 2.0290. Min Range: -2.0290

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1408563 (Python Code)

Max Activating Token Index: 567