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

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

Neuron 1684 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: 0.1143. Min Range: -0.1143

Max Act: 0.1068. Min Act: -0.0001

Data Index: 800027 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0001

Data Index: 300846 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1242024 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1058. Min Act: -0.0001

Data Index: 872868 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1190911 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1019. Min Act: -0.0001

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0957. Min Act: -0.0000

Data Index: 918281 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0913. Min Act: -0.0001

Data Index: 573629 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0980. Min Act: -0.0001

Data Index: 744737 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0975. Min Act: -0.0001

Data Index: 256473 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1013. Min Act: -0.0001

Data Index: 398045 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1290289 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0962. Min Act: -0.0000

Data Index: 333922 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0958. Min Act: -0.0001

Data Index: 434200 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1325277 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1141321 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0888. Min Act: -0.0001

Data Index: 807407 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0881. Min Act: -0.0000

Data Index: 98166 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1212470 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1048685 (C4 (Web Text))

Max Activating Token Index: 906