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

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

Neuron 3126 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.9727. Min Act: -0.0000

Data Index: 1221482 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 7.1112. Min Range: -7.1112

Max Act: 7.1112. Min Act: -0.0000

Data Index: 55589 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.9268. Min Act: -0.0000

Data Index: 1313426 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.6693. Min Act: -0.0000

Data Index: 1162211 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.7577. Min Act: -0.0000

Data Index: 49314 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.7745. Min Act: -0.0000

Data Index: 1153357 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.5054. Min Act: -0.0000

Data Index: 873651 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.6933. Min Act: -0.0000

Data Index: 286705 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.4824. Min Act: -0.0000

Data Index: 81604 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.6770. Min Act: -0.0000

Data Index: 657874 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.7879. Min Act: -0.0000

Data Index: 1194156 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.5915. Min Act: -0.0000

Data Index: 853398 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.6080. Min Act: -0.0000

Data Index: 26345 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.6143. Min Act: -0.0000

Data Index: 802742 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.5446. Min Act: -0.0000

Data Index: 1220377 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.3413. Min Act: -0.0000

Data Index: 1010814 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.7051. Min Act: -0.0000

Data Index: 714273 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.6674. Min Act: -0.0000

Data Index: 815578 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.4792. Min Act: -0.0000

Data Index: 136083 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 7.1112. Min Range: -7.1112

Max Act: 6.4618. Min Act: -0.0000

Data Index: 461053 (C4 (Web Text))

Max Activating Token Index: 473