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

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

Neuron 346 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.5638. Min Act: -0.0001

Data Index: 136784 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.3450. Min Act: -0.0001

Data Index: 192993 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.8046. Min Act: -0.0001

Data Index: 718421 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.3288. Min Act: -0.0001

Data Index: 352894 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.1939. Min Act: -0.0000

Data Index: 785916 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.4799. Min Act: -0.0000

Data Index: 1237694 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.6551. Min Act: -0.0001

Data Index: 1112690 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.3955. Min Act: -0.0001

Data Index: 436651 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.6411. Min Act: -0.0001

Data Index: 751399 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.0946. Min Act: -0.0001

Data Index: 1036408 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.7389. Min Act: -0.0001

Data Index: 219759 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.2165. Min Act: -0.0001

Data Index: 682178 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.6498. Min Act: -0.0001

Data Index: 1342051 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.6640. Min Act: -0.0001

Data Index: 989217 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.9302. Min Act: -0.0001

Data Index: 1196548 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.9250. Min Act: -0.0001

Data Index: 1304168 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.0893. Min Act: -0.0001

Data Index: 701313 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 8.8046. Min Range: -8.8046

Max Act: 8.0832. Min Act: -0.0001

Data Index: 1050038 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.2709. Min Act: -0.0001

Data Index: 579771 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 8.8046. Min Range: -8.8046

Max Act: 7.1414. Min Act: -0.0001

Data Index: 229204 (C4 (Web Text))

Max Activating Token Index: 492