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

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

Neuron 5672 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: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1118292 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0245. Min Act: -0.0002

Data Index: 354930 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0241. Min Act: -0.0002

Data Index: 465671 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1361464 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1360996 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1364668 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1365312 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1361890 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1366367 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1362740 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1363132 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1360764 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1365033 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1365250 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1364957 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1366418 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1365713 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1366850 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1363097 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1364602 (Python Code)

Max Activating Token Index: 1