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

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

Neuron 5213 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1091694 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3263. Min Act: -0.0000

Data Index: 230472 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3030. Min Act: -0.0000

Data Index: 295619 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1224274 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2944. Min Act: -0.0000

Data Index: 905086 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1181571 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1177949 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2442. Min Act: -0.0000

Data Index: 631457 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1214441 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1328332 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1548009 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2077. Min Act: -0.0000

Data Index: 159716 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1513610 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1973. Min Act: -0.0000

Data Index: 223932 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1507363 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1498412 (Python Code)

Max Activating Token Index: 274

Text #16

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1653123 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1653586 (Python Code)

Max Activating Token Index: 543

Text #18

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1591517 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1512245 (Python Code)

Max Activating Token Index: 971