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

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

Neuron 2287 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4717. Min Act: -0.0000

Data Index: 79081 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4736. Min Act: -0.0000

Data Index: 161638 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1327236 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4341. Min Act: -0.0000

Data Index: 945016 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4282. Min Act: -0.0000

Data Index: 793001 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4570. Min Act: -0.0000

Data Index: 457562 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4458. Min Act: -0.0000

Data Index: 568148 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3743. Min Act: -0.0000

Data Index: 634027 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4188. Min Act: -0.0000

Data Index: 167378 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4073. Min Act: -0.0000

Data Index: 89189 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1107939 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3473. Min Act: -0.0000

Data Index: 990495 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3608. Min Act: -0.0000

Data Index: 114078 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3831. Min Act: -0.0000

Data Index: 853679 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1573298 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1439285 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3955. Min Act: -0.0000

Data Index: 939461 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3733. Min Act: -0.0000

Data Index: 493253 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3584. Min Act: -0.0000

Data Index: 436398 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1121028 (C4 (Web Text))

Max Activating Token Index: 670