Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.8249. Min Range: -5.8249

Max Act: 5.8249. Min Act: -0.0000

Data Index: 1577709 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 5.8249. Min Range: -5.8249

Max Act: 5.6164. Min Act: -0.0000

Data Index: 1487238 (Python Code)

Max Activating Token Index: 671

Text #2

Max Range: 5.8249. Min Range: -5.8249

Max Act: 5.2121. Min Act: -0.0000

Data Index: 1470617 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 5.8249. Min Range: -5.8249

Max Act: 5.1731. Min Act: -0.0000

Data Index: 1404228 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.9369. Min Act: -0.0000

Data Index: 1549193 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.9010. Min Act: -0.0000

Data Index: 1434572 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.8043. Min Act: -0.0000

Data Index: 1533728 (Python Code)

Max Activating Token Index: 860

Text #7

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.4573. Min Act: -0.0000

Data Index: 1393263 (Python Code)

Max Activating Token Index: 654

Text #8

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.9482. Min Act: -0.0000

Data Index: 1457967 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.5964. Min Act: -0.0000

Data Index: 1558624 (Python Code)

Max Activating Token Index: 877

Text #10

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.7528. Min Act: -0.0000

Data Index: 1576303 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.5790. Min Act: -0.0000

Data Index: 1599643 (Python Code)

Max Activating Token Index: 687

Text #12

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.7508. Min Act: -0.0000

Data Index: 1481447 (Python Code)

Max Activating Token Index: 641

Text #13

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.9127. Min Act: -0.0000

Data Index: 1582320 (Python Code)

Max Activating Token Index: 352

Text #14

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.7101. Min Act: -0.0000

Data Index: 1432831 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.3523. Min Act: -0.0000

Data Index: 1441293 (Python Code)

Max Activating Token Index: 238

Text #16

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.6884. Min Act: -0.0000

Data Index: 1412168 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.6738. Min Act: -0.0000

Data Index: 1521697 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.5160. Min Act: -0.0000

Data Index: 1483769 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 5.8249. Min Range: -5.8249

Max Act: 4.8107. Min Act: -0.0000

Data Index: 1465292 (Python Code)

Max Activating Token Index: 532