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

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

Neuron 4095 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0714. Min Range: -2.0714

Max Act: 2.0714. Min Act: -0.0000

Data Index: 1585610 (Python Code)

Max Activating Token Index: 502

Text #1

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1389748 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7456. Min Act: -0.0000

Data Index: 1583691 (Python Code)

Max Activating Token Index: 684

Text #3

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1441960 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1566463 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.5527. Min Act: -0.0000

Data Index: 1366642 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1503575 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1387167 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4590. Min Act: -0.0000

Data Index: 1645953 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.5642. Min Act: -0.0001

Data Index: 1416666 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.5546. Min Act: -0.0000

Data Index: 1575603 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4948. Min Act: -0.0000

Data Index: 1633707 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.5836. Min Act: -0.0000

Data Index: 1546300 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4698. Min Act: -0.0000

Data Index: 1631356 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1619434 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1581380 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.3925. Min Act: -0.0000

Data Index: 1460278 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1612270 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4087. Min Act: -0.0000

Data Index: 1544140 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1609478 (Python Code)

Max Activating Token Index: 26