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

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

Neuron 492 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5073. Min Range: -3.5073

Max Act: 3.5073. Min Act: -0.0000

Data Index: 1653624 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 3.5073. Min Range: -3.5073

Max Act: 3.2965. Min Act: -0.0000

Data Index: 1411232 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 3.5073. Min Range: -3.5073

Max Act: 3.2174. Min Act: -0.0000

Data Index: 1586022 (Python Code)

Max Activating Token Index: 772

Text #3

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.9576. Min Act: -0.0000

Data Index: 1543916 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.6588. Min Act: -0.0000

Data Index: 1403963 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.8714. Min Act: -0.0000

Data Index: 1560989 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.9603. Min Act: -0.0000

Data Index: 1563729 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.8155. Min Act: -0.0000

Data Index: 884002 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.7832. Min Act: -0.0000

Data Index: 1459403 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.6420. Min Act: -0.0000

Data Index: 1406324 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.7583. Min Act: -0.0000

Data Index: 1648521 (Python Code)

Max Activating Token Index: 255

Text #11

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.7120. Min Act: -0.0000

Data Index: 1644269 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.6943. Min Act: -0.0000

Data Index: 1384071 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.5841. Min Act: -0.0000

Data Index: 1438123 (Python Code)

Max Activating Token Index: 101

Text #14

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.6984. Min Act: -0.0000

Data Index: 1471549 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.6796. Min Act: -0.0000

Data Index: 1516248 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.7824. Min Act: -0.0000

Data Index: 1430491 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.6280. Min Act: -0.0000

Data Index: 854092 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.4836. Min Act: -0.0000

Data Index: 1644573 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 3.5073. Min Range: -3.5073

Max Act: 2.4900. Min Act: -0.0000

Data Index: 1428675 (Python Code)

Max Activating Token Index: 1016