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

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

Neuron 3948 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: 0.5923. Min Range: -0.5923

Max Act: 0.5923. Min Act: -0.0000

Data Index: 478555 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5923. Min Act: -0.0000

Data Index: 554052 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5653. Min Act: -0.0000

Data Index: 707597 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5626. Min Act: -0.0000

Data Index: 135974 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5546. Min Act: -0.0000

Data Index: 713604 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5634. Min Act: -0.0000

Data Index: 234431 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5439. Min Act: -0.0000

Data Index: 228418 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5067. Min Act: -0.0000

Data Index: 380354 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5415. Min Act: -0.0000

Data Index: 154645 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5384. Min Act: -0.0000

Data Index: 376872 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5180. Min Act: -0.0000

Data Index: 108845 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5163. Min Act: -0.0000

Data Index: 986485 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5161. Min Act: -0.0000

Data Index: 301615 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5083. Min Act: -0.0000

Data Index: 660706 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5474. Min Act: -0.0000

Data Index: 102052 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5375. Min Act: -0.0000

Data Index: 872859 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1210827 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5318. Min Act: -0.0000

Data Index: 38077 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5289. Min Act: -0.0000

Data Index: 889628 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5110. Min Act: -0.0000

Data Index: 989233 (C4 (Web Text))

Max Activating Token Index: 937