Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2492 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.4015. Min Act: -0.0001

Data Index: 433822 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3941. Min Act: -0.0000

Data Index: 879382 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3311. Min Act: -0.0000

Data Index: 396525 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3354. Min Act: -0.0000

Data Index: 727051 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3098. Min Act: -0.0000

Data Index: 135215 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1207535 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2924. Min Act: -0.0000

Data Index: 433294 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3032. Min Act: -0.0000

Data Index: 18066 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2854. Min Act: -0.0000

Data Index: 638665 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1262887 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2624. Min Act: -0.0001

Data Index: 1181523 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2902. Min Act: -0.0000

Data Index: 309934 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1446078 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3152. Min Act: -0.0001

Data Index: 177246 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2741. Min Act: -0.0001

Data Index: 1254232 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1077200 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2824. Min Act: -0.0000

Data Index: 923135 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2657. Min Act: -0.0000

Data Index: 610049 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1482626 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2740. Min Act: -0.0000

Data Index: 937611 (C4 (Web Text))

Max Activating Token Index: 917