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

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

Neuron 346 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.2859. Min Act: -0.0000

Data Index: 1501860 (Python Code)

Max Activating Token Index: 43

Text #1

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.3990. Min Act: 0.0000

Data Index: 1358282 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.4100. Min Act: 0.0000

Data Index: 36358 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.3568. Min Act: -0.0000

Data Index: 1522162 (Python Code)

Max Activating Token Index: 223

Text #4

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.2261. Min Act: -0.0000

Data Index: 920562 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.0905. Min Act: -0.0000

Data Index: 319594 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.2651. Min Act: -0.0000

Data Index: 1029966 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.2499. Min Act: -0.0000

Data Index: 131426 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.2470. Min Act: -0.0000

Data Index: 802292 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.1044. Min Act: -0.0000

Data Index: 192971 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.0974. Min Act: 0.0000

Data Index: 609057 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.0879. Min Act: 0.0000

Data Index: 1117682 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.0685. Min Act: -0.0000

Data Index: 1388502 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.0168. Min Act: 0.0000

Data Index: 1260345 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.1104. Min Act: -0.0000

Data Index: 733802 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.0055. Min Act: -0.0000

Data Index: 455025 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.1243. Min Act: -0.0000

Data Index: 888962 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.0114. Min Act: -0.0000

Data Index: 951959 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 2.4100. Min Range: -2.4100

Max Act: 2.1014. Min Act: -0.0000

Data Index: 627926 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 2.4100. Min Range: -2.4100

Max Act: 1.9682. Min Act: -0.0000

Data Index: 1042190 (C4 (Web Text))

Max Activating Token Index: 478