Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1617692 (Python Code)

Max Activating Token Index: 121

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1589957 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1525108 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1584441 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1631107 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1387032 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1587028 (Python Code)

Max Activating Token Index: 741

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1605341 (Python Code)

Max Activating Token Index: 816

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1611121 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1634488 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1496912 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1393690 (Python Code)

Max Activating Token Index: 851

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1645893 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1504250 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1577245 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1377789 (Python Code)

Max Activating Token Index: 492

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1618680 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1387949 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1496514 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1521866 (Python Code)

Max Activating Token Index: 467