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

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

Neuron 2582 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: 0.1446. Min Range: -0.1446

Max Act: 0.1446. Min Act: -0.0003

Data Index: 231976 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1195. Min Act: -0.0002

Data Index: 822974 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1095. Min Act: -0.0003

Data Index: 478922 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1180830 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0937. Min Act: -0.0003

Data Index: 350475 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1014. Min Act: -0.0003

Data Index: 236691 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1311193 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0974. Min Act: -0.0003

Data Index: 719297 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1143546 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1240736 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0860. Min Act: -0.0003

Data Index: 945364 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0881. Min Act: -0.0002

Data Index: 180838 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0876. Min Act: -0.0003

Data Index: 638237 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0841. Min Act: -0.0003

Data Index: 598984 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0913. Min Act: -0.0003

Data Index: 352490 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0819. Min Act: -0.0003

Data Index: 754424 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0879. Min Act: -0.0003

Data Index: 999393 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0857. Min Act: -0.0003

Data Index: 1096238 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1601435 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0895. Min Act: -0.0003

Data Index: 1048486 (C4 (Web Text))

Max Activating Token Index: 79