Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3170 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.4053. Min Act: -0.0000

Data Index: 774828 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1770. Min Act: -0.0000

Data Index: 947946 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1137. Min Act: -0.0000

Data Index: 217012 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1060. Min Act: -0.0001

Data Index: 501151 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0227. Min Act: -0.0001

Data Index: 98225 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0846. Min Act: -0.0001

Data Index: 719553 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1044013 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.9745. Min Act: -0.0000

Data Index: 402949 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.8745. Min Act: -0.0000

Data Index: 350006 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.9568. Min Act: -0.0000

Data Index: 165530 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1157739 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.9201. Min Act: -0.0001

Data Index: 712598 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.8590. Min Act: -0.0001

Data Index: 716609 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.9033. Min Act: -0.0000

Data Index: 154005 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.8075. Min Act: -0.0001

Data Index: 309624 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.8069. Min Act: -0.0001

Data Index: 1148944 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.8077. Min Act: -0.0001

Data Index: 92961 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1116069 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1338869 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.4053. Min Range: -1.4053

Max Act: 0.8100. Min Act: -0.0001

Data Index: 97864 (C4 (Web Text))

Max Activating Token Index: 62