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

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

Neuron 2207 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.8393. Min Act: -0.0000

Data Index: 579289 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.5506. Min Act: -0.0000

Data Index: 983858 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.3946. Min Act: -0.0000

Data Index: 1485978 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.3696. Min Act: -0.0000

Data Index: 1600716 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.2688. Min Act: -0.0000

Data Index: 1066570 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.2980. Min Act: -0.0000

Data Index: 1494584 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.2269. Min Act: -0.0000

Data Index: 1623614 (Python Code)

Max Activating Token Index: 720

Text #7

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.1181. Min Act: -0.0000

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.1281. Min Act: -0.0000

Data Index: 1649086 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 2.8393. Min Range: -2.8393

Max Act: 2.1758. Min Act: -0.0000

Data Index: 1639419 (Python Code)

Max Activating Token Index: 751

Text #10

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.9861. Min Act: -0.0000

Data Index: 776913 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.8180. Min Act: -0.0000

Data Index: 1147103 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.7673. Min Act: -0.0000

Data Index: 1312187 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.7778. Min Act: -0.0000

Data Index: 1415933 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.6841. Min Act: -0.0000

Data Index: 1206923 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.7186. Min Act: -0.0000

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1628820 (Python Code)

Max Activating Token Index: 494

Text #17

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.5790. Min Act: -0.0000

Data Index: 946878 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1606846 (Python Code)

Max Activating Token Index: 574

Text #19

Max Range: 2.8393. Min Range: -2.8393

Max Act: 1.6469. Min Act: -0.0000

Data Index: 240143 (C4 (Web Text))

Max Activating Token Index: 411