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

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

Neuron 3681 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5780. Min Range: -4.5780

Max Act: 4.5780. Min Act: -0.0000

Data Index: 1471606 (Python Code)

Max Activating Token Index: 569

Text #1

Max Range: 4.5780. Min Range: -4.5780

Max Act: 4.1932. Min Act: -0.0000

Data Index: 1401906 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 4.5780. Min Range: -4.5780

Max Act: 4.1119. Min Act: -0.0000

Data Index: 1428494 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.8929. Min Act: -0.0000

Data Index: 1407368 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.7041. Min Act: -0.0000

Data Index: 1584309 (Python Code)

Max Activating Token Index: 824

Text #5

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.6761. Min Act: -0.0000

Data Index: 1576329 (Python Code)

Max Activating Token Index: 770

Text #6

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.7226. Min Act: -0.0000

Data Index: 1420134 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.5577. Min Act: -0.0000

Data Index: 1434810 (Python Code)

Max Activating Token Index: 588

Text #8

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.8446. Min Act: -0.0000

Data Index: 1460294 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.6424. Min Act: -0.0000

Data Index: 1588354 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.5886. Min Act: -0.0000

Data Index: 1572877 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.5437. Min Act: -0.0000

Data Index: 1535276 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.5586. Min Act: -0.0000

Data Index: 1485806 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.4940. Min Act: -0.0000

Data Index: 1507048 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.4731. Min Act: -0.0000

Data Index: 1407495 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.4734. Min Act: -0.0000

Data Index: 1461620 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.3120. Min Act: 0.0000

Data Index: 1598123 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.4027. Min Act: -0.0000

Data Index: 1464920 (Python Code)

Max Activating Token Index: 390

Text #18

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.3404. Min Act: -0.0000

Data Index: 1600110 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 4.5780. Min Range: -4.5780

Max Act: 3.2811. Min Act: -0.0000

Data Index: 1421544 (Python Code)

Max Activating Token Index: 106