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

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

Neuron 4094 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: 2.7850. Min Range: -2.7850

Max Act: 2.7850. Min Act: -0.0000

Data Index: 1588517 (Python Code)

Max Activating Token Index: 883

Text #1

Max Range: 2.7850. Min Range: -2.7850

Max Act: 2.7191. Min Act: -0.0000

Data Index: 1448730 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 2.7850. Min Range: -2.7850

Max Act: 2.7715. Min Act: -0.0000

Data Index: 1367603 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.9700. Min Act: -0.0000

Data Index: 1494075 (Python Code)

Max Activating Token Index: 367

Text #4

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.8188. Min Act: -0.0000

Data Index: 1563078 (Python Code)

Max Activating Token Index: 836

Text #5

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.8483. Min Act: -0.0000

Data Index: 1152935 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1224210 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.6948. Min Act: -0.0000

Data Index: 411302 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.6795. Min Act: -0.0000

Data Index: 1495508 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1530665 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.6386. Min Act: -0.0000

Data Index: 1577005 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.6137. Min Act: -0.0000

Data Index: 152919 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1308190 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1372248 (Python Code)

Max Activating Token Index: 955

Text #14

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1381972 (Python Code)

Max Activating Token Index: 551

Text #15

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1202196 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1413489 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.3405. Min Act: -0.0000

Data Index: 17589 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.3899. Min Act: -0.0000

Data Index: 1632080 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1599626 (Python Code)

Max Activating Token Index: 135