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

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

Neuron 859 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0002

Data Index: 691087 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0991. Min Act: -0.0002

Data Index: 719085 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0967. Min Act: -0.0002

Data Index: 16057 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1055668 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0959. Min Act: -0.0002

Data Index: 645248 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1052968 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0909. Min Act: -0.0002

Data Index: 114669 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1034321 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0902. Min Act: -0.0002

Data Index: 360198 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0898. Min Act: -0.0002

Data Index: 43819 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0895. Min Act: -0.0002

Data Index: 66356 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0891. Min Act: -0.0002

Data Index: 815715 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1121101 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0872. Min Act: -0.0002

Data Index: 541025 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0863. Min Act: -0.0002

Data Index: 817438 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0864. Min Act: -0.0002

Data Index: 386324 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1432862 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1112213 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0837. Min Act: -0.0002

Data Index: 870476 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1052505 (C4 (Web Text))

Max Activating Token Index: 403