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

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

Neuron 399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2536. Min Act: -0.0000

Data Index: 194135 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1239790 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1102510 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1038476 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1374684 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1253234 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1159872 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1041. Min Act: -0.0000

Data Index: 327191 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0877. Min Act: -0.0000

Data Index: 356276 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0918. Min Act: -0.0000

Data Index: 75746 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0880. Min Act: -0.0000

Data Index: 644049 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0932. Min Act: -0.0000

Data Index: 713921 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0893. Min Act: -0.0000

Data Index: 385414 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1230097 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0859. Min Act: -0.0000

Data Index: 875925 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0882. Min Act: -0.0000

Data Index: 446170 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0872. Min Act: -0.0000

Data Index: 745634 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0875. Min Act: -0.0000

Data Index: 777991 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0869. Min Act: -0.0000

Data Index: 816864 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1161883 (C4 (Web Text))

Max Activating Token Index: 837