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

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

Neuron 1738 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: 2.4060. Min Range: -2.4060

Max Act: 2.4060. Min Act: -0.0000

Data Index: 840921 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.9026. Min Act: -0.0000

Data Index: 1653029 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 2.4060. Min Range: -2.4060

Max Act: 2.1663. Min Act: -0.0000

Data Index: 629809 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.8178. Min Act: -0.0000

Data Index: 147686 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1227574 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.5654. Min Act: -0.0000

Data Index: 1561529 (Python Code)

Max Activating Token Index: 890

Text #6

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.4246. Min Act: -0.0000

Data Index: 595141 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.3967. Min Act: -0.0000

Data Index: 832107 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1365146 (Python Code)

Max Activating Token Index: 806

Text #9

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1523206 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.3552. Min Act: -0.0000

Data Index: 291925 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.3288. Min Act: -0.0000

Data Index: 404792 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.4416. Min Act: -0.0000

Data Index: 249515 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.3700. Min Act: -0.0000

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.4737. Min Act: -0.0000

Data Index: 1599002 (Python Code)

Max Activating Token Index: 205

Text #15

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.2926. Min Act: -0.0000

Data Index: 964831 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1499512 (Python Code)

Max Activating Token Index: 763

Text #17

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.1572. Min Act: -0.0000

Data Index: 361493 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1371621 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 2.4060. Min Range: -2.4060

Max Act: 1.3324. Min Act: -0.0000

Data Index: 151550 (C4 (Web Text))

Max Activating Token Index: 205