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

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

Neuron 654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0003

Data Index: 537010 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1074. Min Act: -0.0003

Data Index: 372688 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1064. Min Act: -0.0003

Data Index: 1337428 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1128. Min Act: -0.0003

Data Index: 99284 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1030. Min Act: -0.0003

Data Index: 702320 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0974. Min Act: -0.0003

Data Index: 6812 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0915. Min Act: -0.0003

Data Index: 602171 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1007. Min Act: -0.0003

Data Index: 897754 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1324920 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0912. Min Act: -0.0002

Data Index: 652046 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0841. Min Act: -0.0003

Data Index: 1170996 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1029453 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0962. Min Act: -0.0003

Data Index: 1172 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0922. Min Act: -0.0003

Data Index: 1079070 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0911. Min Act: -0.0003

Data Index: 634028 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1257484 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0836. Min Act: -0.0003

Data Index: 529025 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1041896 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0883. Min Act: -0.0003

Data Index: 572115 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0884. Min Act: -0.0002

Data Index: 78644 (C4 (Web Text))

Max Activating Token Index: 930