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

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

Neuron 1637 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: 0.3621. Min Range: -0.3621

Max Act: 0.3621. Min Act: -0.0000

Data Index: 913875 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3458. Min Act: -0.0000

Data Index: 560894 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3298. Min Act: -0.0000

Data Index: 454695 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3547. Min Act: -0.0000

Data Index: 423040 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3446. Min Act: -0.0000

Data Index: 182743 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3288. Min Act: 0.0001

Data Index: 1009879 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1351623 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3094. Min Act: -0.0000

Data Index: 230888 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3156. Min Act: -0.0000

Data Index: 724543 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3041. Min Act: -0.0000

Data Index: 368807 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3150. Min Act: -0.0000

Data Index: 769899 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3098. Min Act: -0.0000

Data Index: 315865 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3065. Min Act: -0.0000

Data Index: 649775 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2968. Min Act: -0.0000

Data Index: 367667 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3067. Min Act: -0.0000

Data Index: 12024 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3022. Min Act: -0.0000

Data Index: 497545 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3033. Min Act: -0.0000

Data Index: 672903 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3141. Min Act: -0.0000

Data Index: 98983 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3101. Min Act: -0.0000

Data Index: 33562 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1156078 (C4 (Web Text))

Max Activating Token Index: 831