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

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

Neuron 4024 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1375692 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1578626 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1620420 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1449278 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0709. Min Act: -0.0002

Data Index: 573690 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1377948 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1524118 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1520097 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1411476 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1557203 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1480144 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1401373 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1444845 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1559955 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1621835 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1577519 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0593. Min Act: -0.0001

Data Index: 369384 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0523. Min Act: -0.0002

Data Index: 104375 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1349273 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1385627 (Python Code)

Max Activating Token Index: 161