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

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

Neuron 3312 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.4989. Min Act: -0.0000

Data Index: 208534 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.4111. Min Act: -0.0000

Data Index: 310731 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1045917 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1193921 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1003969 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1060600 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2092. Min Act: -0.0000

Data Index: 27480 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2654. Min Act: -0.0000

Data Index: 563158 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2470. Min Act: -0.0000

Data Index: 789244 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1756. Min Act: -0.0000

Data Index: 251370 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1931. Min Act: -0.0000

Data Index: 253696 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1293878 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2318. Min Act: -0.0000

Data Index: 48244 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.2148. Min Act: -0.0000

Data Index: 398465 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0682. Min Act: -0.0000

Data Index: 876325 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1093. Min Act: -0.0000

Data Index: 382569 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1098. Min Act: -0.0000

Data Index: 138294 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1212622 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1702. Min Act: -0.0000

Data Index: 18343 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1029119 (C4 (Web Text))

Max Activating Token Index: 624