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

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

Neuron 1705 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: 0.1343. Min Range: -0.1343

Max Act: 0.1343. Min Act: -0.0002

Data Index: 1425565 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1063367 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1179. Min Act: -0.0002

Data Index: 888881 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1446262 (Python Code)

Max Activating Token Index: 800

Text #4

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1592772 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0938. Min Act: -0.0002

Data Index: 484584 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1632358 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1374031 (Python Code)

Max Activating Token Index: 387

Text #8

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0957. Min Act: -0.0002

Data Index: 538527 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0913. Min Act: -0.0002

Data Index: 87212 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0894. Min Act: -0.0002

Data Index: 761007 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0893. Min Act: -0.0002

Data Index: 509079 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0916. Min Act: -0.0002

Data Index: 741498 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0884. Min Act: -0.0002

Data Index: 199253 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1055051 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1088971 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0855. Min Act: -0.0002

Data Index: 910002 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0861. Min Act: -0.0002

Data Index: 33823 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1484284 (Python Code)

Max Activating Token Index: 989

Text #19

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0805. Min Act: -0.0002

Data Index: 655705 (C4 (Web Text))

Max Activating Token Index: 249