Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5733. Min Act: -0.0001

Data Index: 515595 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5991. Min Act: -0.0001

Data Index: 1040923 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5137. Min Act: -0.0001

Data Index: 171909 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4740. Min Act: -0.0001

Data Index: 1405098 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4863. Min Act: -0.0001

Data Index: 661783 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3035. Min Act: -0.0001

Data Index: 1517973 (Python Code)

Max Activating Token Index: 285

Text #6

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3652. Min Act: -0.0001

Data Index: 1419754 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1179297 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.2573. Min Act: -0.0001

Data Index: 18490 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3406. Min Act: -0.0001

Data Index: 575920 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3249. Min Act: -0.0001

Data Index: 1548479 (Python Code)

Max Activating Token Index: 822

Text #11

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.2812. Min Act: -0.0001

Data Index: 461224 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.2938. Min Act: -0.0001

Data Index: 1656096 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.1908. Min Act: -0.0001

Data Index: 591330 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1039283 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.1462. Min Act: -0.0001

Data Index: 1170986 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.2225. Min Act: -0.0001

Data Index: 316688 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.2050. Min Act: -0.0001

Data Index: 1205421 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.1969. Min Act: -0.0001

Data Index: 1239508 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.1595. Min Act: -0.0001

Data Index: 394314 (C4 (Web Text))

Max Activating Token Index: 5