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

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

Neuron 1806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.4920. Min Act: -0.0000

Data Index: 1390250 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1482482 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1405442 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1571455 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.3052. Min Act: -0.0000

Data Index: 1592432 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1543726 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1380920 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1486168 (Python Code)

Max Activating Token Index: 950

Text #8

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2151. Min Act: -0.0000

Data Index: 1633869 (Python Code)

Max Activating Token Index: 685

Text #9

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1608194 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1427975 (Python Code)

Max Activating Token Index: 821

Text #11

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1393555 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2334. Min Act: -0.0000

Data Index: 1396659 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1493370 (Python Code)

Max Activating Token Index: 804

Text #14

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.3043. Min Act: -0.0000

Data Index: 1369129 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1409111 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1364762 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1408088 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1560377 (Python Code)

Max Activating Token Index: 699

Text #19

Max Range: 1.4920. Min Range: -1.4920

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1377879 (Python Code)

Max Activating Token Index: 942