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

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

Neuron 3026 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5751. Min Act: 0.0000

Data Index: 27354 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.8993. Min Act: 0.0000

Data Index: 347418 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.8821. Min Act: -0.0000

Data Index: 791368 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.4617. Min Act: -0.0000

Data Index: 216980 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.5250. Min Act: -0.0000

Data Index: 634126 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.2985. Min Act: -0.0000

Data Index: 1268738 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.2581. Min Act: 0.0001

Data Index: 926400 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.3639. Min Act: -0.0000

Data Index: 1036841 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.2664. Min Act: -0.0000

Data Index: 1213393 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.1656. Min Act: -0.0000

Data Index: 447418 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.0569. Min Act: -0.0000

Data Index: 324788 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 3.5751. Min Range: -3.5751

Max Act: 2.0159. Min Act: 0.0000

Data Index: 827018 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.9077. Min Act: 0.0000

Data Index: 878245 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.8131. Min Act: -0.0000

Data Index: 346585 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.9048. Min Act: -0.0000

Data Index: 754020 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.8925. Min Act: 0.0001

Data Index: 669363 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.8110. Min Act: -0.0000

Data Index: 1071311 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.6959. Min Act: 0.0001

Data Index: 843005 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.7636. Min Act: 0.0000

Data Index: 1282616 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 3.5751. Min Range: -3.5751

Max Act: 1.8406. Min Act: 0.0000

Data Index: 864896 (C4 (Web Text))

Max Activating Token Index: 616