Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 699 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1536411 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2158. Min Act: -0.0001

Data Index: 1426489 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1454621 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2160. Min Act: -0.0001

Data Index: 1468741 (Python Code)

Max Activating Token Index: 426

Text #4

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1463686 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1130228 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1467202 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1969. Min Act: -0.0001

Data Index: 618219 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1909. Min Act: -0.0001

Data Index: 227484 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1459118 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1396055 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1513494 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1429069 (Python Code)

Max Activating Token Index: 792

Text #13

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1499341 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1909. Min Act: -0.0001

Data Index: 165816 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1552489 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1891. Min Act: -0.0001

Data Index: 241278 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1950. Min Act: -0.0001

Data Index: 4249 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1815. Min Act: -0.0001

Data Index: 502693 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.2221. Min Range: -0.2221

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1466477 (Python Code)

Max Activating Token Index: 151