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

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

Neuron 915 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.6315. Min Act: -0.0000

Data Index: 440300 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.6114. Min Act: -0.0000

Data Index: 399209 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.4460. Min Act: -0.0000

Data Index: 290306 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.2191. Min Act: -0.0000

Data Index: 125408 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.1407. Min Act: 0.0000

Data Index: 1286699 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.0661. Min Act: -0.0000

Data Index: 324323 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.0584. Min Act: -0.0000

Data Index: 941303 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.0474. Min Act: 0.0000

Data Index: 135325 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.0422. Min Act: -0.0000

Data Index: 118467 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9905. Min Act: -0.0000

Data Index: 684733 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9843. Min Act: -0.0000

Data Index: 795157 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9855. Min Act: -0.0000

Data Index: 655418 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9742. Min Act: 0.0002

Data Index: 334174 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 2.6315. Min Range: -2.6315

Max Act: 2.0544. Min Act: -0.0000

Data Index: 688845 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9233. Min Act: -0.0000

Data Index: 1296782 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9194. Min Act: -0.0000

Data Index: 643435 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9192. Min Act: -0.0000

Data Index: 113223 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.9042. Min Act: -0.0000

Data Index: 842706 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.8934. Min Act: -0.0000

Data Index: 1255177 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 2.6315. Min Range: -2.6315

Max Act: 1.8783. Min Act: -0.0000

Data Index: 99044 (C4 (Web Text))

Max Activating Token Index: 965