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

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

Neuron 970 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: 0.3543. Min Range: -0.3543

Max Act: 0.3543. Min Act: -0.0000

Data Index: 607672 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3258. Min Act: -0.0000

Data Index: 887577 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3134. Min Act: -0.0000

Data Index: 78051 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1226957 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2974. Min Act: -0.0000

Data Index: 135366 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3045. Min Act: -0.0000

Data Index: 446700 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2999. Min Act: -0.0000

Data Index: 578308 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2801. Min Act: -0.0000

Data Index: 104590 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1241423 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2929. Min Act: -0.0000

Data Index: 940744 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2818. Min Act: -0.0000

Data Index: 902727 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3014. Min Act: -0.0000

Data Index: 564255 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2777. Min Act: -0.0000

Data Index: 147459 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1205204 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2611. Min Act: -0.0000

Data Index: 472292 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3001. Min Act: -0.0000

Data Index: 745548 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2687. Min Act: -0.0000

Data Index: 204200 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2613. Min Act: -0.0000

Data Index: 107581 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2687. Min Act: -0.0000

Data Index: 574376 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2784. Min Act: -0.0000

Data Index: 64500 (C4 (Web Text))

Max Activating Token Index: 397