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

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

Neuron 2060 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: 3.0837. Min Range: -3.0837

Max Act: 3.0837. Min Act: -0.0000

Data Index: 1232702 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.4747. Min Act: -0.0000

Data Index: 448209 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.3669. Min Act: -0.0000

Data Index: 806267 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.4905. Min Act: -0.0000

Data Index: 1201099 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.1704. Min Act: -0.0000

Data Index: 1179709 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.1992. Min Act: -0.0000

Data Index: 852617 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.0115. Min Act: -0.0000

Data Index: 1164667 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.7404. Min Act: -0.0000

Data Index: 463719 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.9537. Min Act: -0.0000

Data Index: 658508 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.9417. Min Act: -0.0000

Data Index: 628213 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.0211. Min Act: -0.0000

Data Index: 174136 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.8605. Min Act: -0.0000

Data Index: 1140348 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.8115. Min Act: -0.0000

Data Index: 878825 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.7928. Min Act: -0.0000

Data Index: 691758 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.0220. Min Act: -0.0000

Data Index: 1188175 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1200052 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.8053. Min Act: -0.0000

Data Index: 404468 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.7538. Min Act: -0.0000

Data Index: 123615 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.6411. Min Act: -0.0000

Data Index: 662525 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 3.0837. Min Range: -3.0837

Max Act: 1.8359. Min Act: -0.0000

Data Index: 787623 (C4 (Web Text))

Max Activating Token Index: 63