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

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

Neuron 1195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1287563 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3833. Min Act: -0.0000

Data Index: 69396 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3710. Min Act: -0.0000

Data Index: 750000 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3331. Min Act: -0.0000

Data Index: 505136 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3243. Min Act: -0.0000

Data Index: 323453 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3314. Min Act: -0.0000

Data Index: 903540 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2977. Min Act: -0.0000

Data Index: 405436 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2857. Min Act: -0.0000

Data Index: 392388 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2884. Min Act: -0.0000

Data Index: 563204 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2981. Min Act: -0.0000

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3178. Min Act: -0.0000

Data Index: 856107 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2949. Min Act: -0.0000

Data Index: 47143 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2908. Min Act: -0.0000

Data Index: 162127 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1131289 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2760. Min Act: -0.0000

Data Index: 745960 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2855. Min Act: -0.0000

Data Index: 630437 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2966. Min Act: -0.0000

Data Index: 637644 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2734. Min Act: -0.0000

Data Index: 144980 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1304928 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1161149 (C4 (Web Text))

Max Activating Token Index: 698