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

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

Neuron 2731 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: 1.0899. Min Range: -1.0899

Max Act: 1.0899. Min Act: -0.0001

Data Index: 1620231 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9665. Min Act: -0.0001

Data Index: 1637939 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 1.0899. Min Range: -1.0899

Max Act: 1.0102. Min Act: -0.0001

Data Index: 1380704 (Python Code)

Max Activating Token Index: 726

Text #3

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8852. Min Act: -0.0001

Data Index: 1551111 (Python Code)

Max Activating Token Index: 838

Text #4

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9456. Min Act: -0.0001

Data Index: 1512072 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9144. Min Act: -0.0001

Data Index: 1501955 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9654. Min Act: -0.0001

Data Index: 1650455 (Python Code)

Max Activating Token Index: 272

Text #7

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9307. Min Act: -0.0001

Data Index: 1548981 (Python Code)

Max Activating Token Index: 519

Text #8

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8749. Min Act: -0.0001

Data Index: 1597366 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8616. Min Act: -0.0001

Data Index: 1596407 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8857. Min Act: -0.0001

Data Index: 1442813 (Python Code)

Max Activating Token Index: 489

Text #11

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8721. Min Act: -0.0001

Data Index: 1535129 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8428. Min Act: -0.0001

Data Index: 1380925 (Python Code)

Max Activating Token Index: 300

Text #13

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8363. Min Act: -0.0001

Data Index: 1578316 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8328. Min Act: -0.0001

Data Index: 1624407 (Python Code)

Max Activating Token Index: 412

Text #15

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8546. Min Act: -0.0001

Data Index: 1487520 (Python Code)

Max Activating Token Index: 998

Text #16

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8715. Min Act: -0.0001

Data Index: 1565529 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8149. Min Act: -0.0001

Data Index: 1637436 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8141. Min Act: -0.0001

Data Index: 1362974 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8113. Min Act: -0.0001

Data Index: 1385930 (Python Code)

Max Activating Token Index: 131