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

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

Neuron 2159 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5203. Min Act: -0.0000

Data Index: 488786 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4650. Min Act: -0.0000

Data Index: 920979 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4530. Min Act: -0.0000

Data Index: 76044 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4614. Min Act: -0.0000

Data Index: 699994 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4581. Min Act: -0.0000

Data Index: 710304 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4446. Min Act: -0.0000

Data Index: 582376 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1138434 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4020. Min Act: -0.0000

Data Index: 324789 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4151. Min Act: -0.0000

Data Index: 975157 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3989. Min Act: -0.0000

Data Index: 627607 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3965. Min Act: -0.0000

Data Index: 131837 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3945. Min Act: -0.0000

Data Index: 550657 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4051. Min Act: -0.0000

Data Index: 508918 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3875. Min Act: -0.0000

Data Index: 489051 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1190694 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3913. Min Act: -0.0000

Data Index: 689703 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3705. Min Act: -0.0000

Data Index: 494500 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1019090 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1206287 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3826. Min Act: -0.0000

Data Index: 460964 (C4 (Web Text))

Max Activating Token Index: 864