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

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

Neuron 2704 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: 1.8018. Min Range: -1.8018

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1357169 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.5744. Min Act: -0.0000

Data Index: 664693 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.3797. Min Act: -0.0000

Data Index: 550205 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.4228. Min Act: -0.0000

Data Index: 553528 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.3244. Min Act: -0.0000

Data Index: 664134 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2320. Min Act: -0.0000

Data Index: 81395 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2215. Min Act: -0.0000

Data Index: 1126693 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.3550. Min Act: -0.0000

Data Index: 903806 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2024. Min Act: -0.0000

Data Index: 463181 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.1902. Min Act: -0.0000

Data Index: 152472 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2306. Min Act: -0.0000

Data Index: 703437 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2551. Min Act: -0.0000

Data Index: 55775 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.1724. Min Act: -0.0000

Data Index: 411265 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.3980. Min Act: -0.0000

Data Index: 299714 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.3180. Min Act: -0.0000

Data Index: 1311588 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.1691. Min Act: -0.0000

Data Index: 809492 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.1987. Min Act: -0.0000

Data Index: 936817 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2358. Min Act: -0.0000

Data Index: 87200 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2176. Min Act: -0.0000

Data Index: 409564 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2370. Min Act: -0.0000

Data Index: 167860 (C4 (Web Text))

Max Activating Token Index: 724