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

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

Neuron 4756 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7475. Min Range: -3.7475

Max Act: 3.6141. Min Act: -0.0001

Data Index: 1539295 (Python Code)

Max Activating Token Index: 333

Text #1

Max Range: 3.7475. Min Range: -3.7475

Max Act: 3.7475. Min Act: -0.0000

Data Index: 1510886 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 3.7475. Min Range: -3.7475

Max Act: 3.3680. Min Act: -0.0000

Data Index: 1511962 (Python Code)

Max Activating Token Index: 241

Text #3

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.7437. Min Act: -0.0001

Data Index: 1483170 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.6355. Min Act: -0.0001

Data Index: 1452941 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.7676. Min Act: -0.0001

Data Index: 1494590 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.7467. Min Act: -0.0000

Data Index: 1561539 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.5806. Min Act: -0.0001

Data Index: 1380333 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.5805. Min Act: -0.0001

Data Index: 1415462 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.6562. Min Act: -0.0000

Data Index: 1575606 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.4979. Min Act: -0.0000

Data Index: 1650344 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.5076. Min Act: -0.0001

Data Index: 1565243 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.8882. Min Act: -0.0001

Data Index: 1363793 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.3284. Min Act: -0.0001

Data Index: 1523248 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.5305. Min Act: -0.0001

Data Index: 1518559 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.5131. Min Act: -0.0001

Data Index: 1393294 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.2512. Min Act: -0.0001

Data Index: 1628288 (Python Code)

Max Activating Token Index: 986

Text #17

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.4990. Min Act: -0.0001

Data Index: 1610923 (Python Code)

Max Activating Token Index: 487

Text #18

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.5189. Min Act: -0.0001

Data Index: 1385162 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 3.7475. Min Range: -3.7475

Max Act: 2.2302. Min Act: -0.0001

Data Index: 1392192 (Python Code)

Max Activating Token Index: 661