Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 300 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1296006 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7153. Min Act: -0.0000

Data Index: 697342 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5851. Min Act: -0.0000

Data Index: 873947 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5327. Min Act: -0.0000

Data Index: 976097 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5565. Min Act: -0.0000

Data Index: 962867 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5000. Min Act: -0.0000

Data Index: 508095 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1132347 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1047024 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4736. Min Act: -0.0000

Data Index: 558701 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1337995 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4504. Min Act: -0.0000

Data Index: 379774 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5021. Min Act: -0.0000

Data Index: 67659 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5039. Min Act: -0.0000

Data Index: 39498 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4039. Min Act: -0.0000

Data Index: 55737 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1316996 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4060. Min Act: -0.0000

Data Index: 293046 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.3895. Min Act: -0.0000

Data Index: 896296 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4345. Min Act: -0.0000

Data Index: 578635 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4130. Min Act: -0.0000

Data Index: 779110 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.4294. Min Act: -0.0000

Data Index: 340741 (C4 (Web Text))

Max Activating Token Index: 940