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

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

Neuron 2246 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: 5.8577. Min Range: -5.8577

Max Act: 5.8577. Min Act: -0.0000

Data Index: 538964 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 5.8577. Min Range: -5.8577

Max Act: 5.0044. Min Act: -0.0000

Data Index: 119815 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 5.8577. Min Range: -5.8577

Max Act: 5.3520. Min Act: -0.0000

Data Index: 426577 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.9775. Min Act: -0.0000

Data Index: 509989 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.7988. Min Act: -0.0000

Data Index: 78255 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.7458. Min Act: -0.0000

Data Index: 1113028 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.8810. Min Act: -0.0000

Data Index: 593452 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.6107. Min Act: -0.0000

Data Index: 388377 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.9281. Min Act: -0.0000

Data Index: 443794 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.5823. Min Act: -0.0000

Data Index: 877957 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.3648. Min Act: -0.0000

Data Index: 795251 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.5144. Min Act: -0.0000

Data Index: 1552 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.3202. Min Act: -0.0000

Data Index: 5625 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.4327. Min Act: -0.0000

Data Index: 1347808 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.4070. Min Act: -0.0000

Data Index: 410551 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.3966. Min Act: -0.0000

Data Index: 583078 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.1708. Min Act: -0.0000

Data Index: 712773 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.2640. Min Act: -0.0000

Data Index: 851751 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.0714. Min Act: -0.0000

Data Index: 489597 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 5.8577. Min Range: -5.8577

Max Act: 4.3335. Min Act: -0.0000

Data Index: 678730 (C4 (Web Text))

Max Activating Token Index: 625