Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1854 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2352. Min Act: -0.0002

Data Index: 409098 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2384. Min Act: -0.0002

Data Index: 368261 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2026. Min Act: -0.0002

Data Index: 1248164 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2027. Min Act: -0.0002

Data Index: 22343 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2117. Min Act: -0.0002

Data Index: 389936 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2071. Min Act: -0.0002

Data Index: 87606 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1987. Min Act: -0.0002

Data Index: 267414 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1985. Min Act: -0.0002

Data Index: 588851 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1973. Min Act: -0.0002

Data Index: 1036916 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1948. Min Act: -0.0002

Data Index: 131614 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2002. Min Act: -0.0002

Data Index: 913058 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2024. Min Act: -0.0002

Data Index: 887275 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1945. Min Act: -0.0002

Data Index: 114953 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1854. Min Act: -0.0002

Data Index: 934915 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2000. Min Act: -0.0002

Data Index: 1347074 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2007. Min Act: -0.0002

Data Index: 312943 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1972. Min Act: -0.0002

Data Index: 626898 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1962. Min Act: -0.0002

Data Index: 597303 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1997. Min Act: -0.0002

Data Index: 1221488 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2042. Min Act: -0.0002

Data Index: 39816 (C4 (Web Text))

Max Activating Token Index: 706