Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2884 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.4588. Min Act: -0.0001

Data Index: 1459331 (Python Code)

Max Activating Token Index: 416

Text #1

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.3096. Min Act: -0.0001

Data Index: 1390888 (Python Code)

Max Activating Token Index: 886

Text #2

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.3966. Min Act: -0.0001

Data Index: 1603026 (Python Code)

Max Activating Token Index: 781

Text #3

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.3357. Min Act: -0.0001

Data Index: 1548938 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.2658. Min Act: -0.0001

Data Index: 1415822 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.3875. Min Act: -0.0001

Data Index: 1500307 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.1698. Min Act: -0.0001

Data Index: 1432016 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.1686. Min Act: -0.0001

Data Index: 1620045 (Python Code)

Max Activating Token Index: 1001

Text #8

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.1573. Min Act: -0.0001

Data Index: 1476136 (Python Code)

Max Activating Token Index: 763

Text #9

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.0042. Min Act: -0.0001

Data Index: 1645285 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.0930. Min Act: -0.0001

Data Index: 1647491 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.0819. Min Act: -0.0001

Data Index: 1635286 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.1304. Min Act: -0.0001

Data Index: 1429147 (Python Code)

Max Activating Token Index: 544

Text #13

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.2099. Min Act: -0.0001

Data Index: 1446717 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 3.4588. Min Range: -3.4588

Max Act: 2.8771. Min Act: -0.0001

Data Index: 1387593 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 3.4588. Min Range: -3.4588

Max Act: 3.0610. Min Act: -0.0001

Data Index: 1580873 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 3.4588. Min Range: -3.4588

Max Act: 2.8464. Min Act: -0.0001

Data Index: 1536607 (Python Code)

Max Activating Token Index: 232

Text #17

Max Range: 3.4588. Min Range: -3.4588

Max Act: 2.9603. Min Act: -0.0001

Data Index: 1489695 (Python Code)

Max Activating Token Index: 966

Text #18

Max Range: 3.4588. Min Range: -3.4588

Max Act: 2.8369. Min Act: -0.0001

Data Index: 1564650 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 3.4588. Min Range: -3.4588

Max Act: 2.8099. Min Act: -0.0001

Data Index: 1490902 (Python Code)

Max Activating Token Index: 835