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

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

Neuron 2158 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1104203 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.2421. Min Act: -0.0001

Data Index: 142638 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.1511. Min Act: -0.0001

Data Index: 330529 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1134159 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.1130. Min Act: -0.0001

Data Index: 760619 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.0637. Min Act: -0.0001

Data Index: 369125 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.0289. Min Act: -0.0001

Data Index: 756015 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9841. Min Act: -0.0001

Data Index: 1253669 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.0362. Min Act: -0.0000

Data Index: 401277 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.4652. Min Range: -1.4652

Max Act: 1.0010. Min Act: -0.0001

Data Index: 30609 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9768. Min Act: -0.0001

Data Index: 455942 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1000619 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9535. Min Act: -0.0000

Data Index: 607431 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9471. Min Act: -0.0000

Data Index: 51628 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9482. Min Act: -0.0001

Data Index: 1072972 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9913. Min Act: -0.0001

Data Index: 849685 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9437. Min Act: -0.0001

Data Index: 650591 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9042. Min Act: -0.0001

Data Index: 367994 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.8526. Min Act: -0.0000

Data Index: 994428 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.4652. Min Range: -1.4652

Max Act: 0.9203. Min Act: -0.0000

Data Index: 329467 (C4 (Web Text))

Max Activating Token Index: 22