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

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

Neuron 3714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.8762. Min Act: -0.0001

Data Index: 595004 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.5447. Min Act: -0.0000

Data Index: 20328 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.3462. Min Act: -0.0000

Data Index: 193990 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1188098 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.3142. Min Act: -0.0000

Data Index: 139806 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.3470. Min Act: -0.0001

Data Index: 827775 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.3105. Min Act: 0.0001

Data Index: 530290 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1039335 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2840. Min Act: -0.0000

Data Index: 988008 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.3131. Min Act: -0.0000

Data Index: 735399 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1109903 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2844. Min Act: -0.0000

Data Index: 61199 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1320995 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1123958 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2718. Min Act: 0.0001

Data Index: 78033 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2565. Min Act: 0.0000

Data Index: 1220057 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2736. Min Act: -0.0000

Data Index: 644617 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2813. Min Act: -0.0001

Data Index: 1351 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2727. Min Act: -0.0000

Data Index: 424352 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.2583. Min Act: -0.0000

Data Index: 826954 (C4 (Web Text))

Max Activating Token Index: 212