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

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

Neuron 1924 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.5235. Min Act: -0.0000

Data Index: 1643143 (Python Code)

Max Activating Token Index: 253

Text #1

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.9413. Min Act: -0.0000

Data Index: 1412605 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.9269. Min Act: -0.0000

Data Index: 1589644 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.1580. Min Act: -0.0000

Data Index: 1459372 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.9754. Min Act: -0.0000

Data Index: 1382834 (Python Code)

Max Activating Token Index: 478

Text #5

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.9631. Min Act: -0.0000

Data Index: 1414067 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.7824. Min Act: -0.0000

Data Index: 1529099 (Python Code)

Max Activating Token Index: 500

Text #7

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.6524. Min Act: -0.0000

Data Index: 1478065 (Python Code)

Max Activating Token Index: 685

Text #8

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.6849. Min Act: -0.0000

Data Index: 1588955 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.6434. Min Act: -0.0000

Data Index: 1402577 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.4891. Min Act: -0.0000

Data Index: 1653958 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.4709. Min Act: -0.0000

Data Index: 1599288 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.5811. Min Act: -0.0000

Data Index: 1549798 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.5805. Min Act: -0.0000

Data Index: 1510077 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.5550. Min Act: -0.0000

Data Index: 1542996 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.4153. Min Act: -0.0000

Data Index: 1518756 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.5188. Min Act: -0.0000

Data Index: 1425960 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.4861. Min Act: -0.0000

Data Index: 1571791 (Python Code)

Max Activating Token Index: 545

Text #18

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.4746. Min Act: -0.0000

Data Index: 1530276 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 3.5235. Min Range: -3.5235

Max Act: 2.5982. Min Act: -0.0000

Data Index: 1520869 (Python Code)

Max Activating Token Index: 43