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

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

Neuron 766 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4697. Min Act: -0.0002

Data Index: 1311515 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4976. Min Act: -0.0002

Data Index: 88799 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4853. Min Act: -0.0002

Data Index: 571450 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4465. Min Act: -0.0002

Data Index: 488195 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4669. Min Act: -0.0002

Data Index: 631250 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4371. Min Act: -0.0002

Data Index: 751367 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4325. Min Act: -0.0002

Data Index: 737266 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4454. Min Act: -0.0002

Data Index: 376827 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4160. Min Act: -0.0002

Data Index: 930337 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4371. Min Act: -0.0002

Data Index: 577501 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3696. Min Act: -0.0002

Data Index: 192874 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4026. Min Act: -0.0002

Data Index: 680759 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4030. Min Act: -0.0002

Data Index: 925463 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4110. Min Act: -0.0002

Data Index: 452093 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4354. Min Act: -0.0002

Data Index: 1037471 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4079. Min Act: -0.0002

Data Index: 478036 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3894. Min Act: -0.0002

Data Index: 1146859 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3815. Min Act: -0.0002

Data Index: 37552 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3642. Min Act: -0.0002

Data Index: 195960 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4223. Min Act: -0.0002

Data Index: 712225 (C4 (Web Text))

Max Activating Token Index: 284