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

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

Neuron 1586 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: 0.1066. Min Range: -0.1066

Max Act: 0.1061. Min Act: -0.0001

Data Index: 570553 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1278269 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1020. Min Act: -0.0001

Data Index: 527435 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1108111 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0990. Min Act: -0.0001

Data Index: 474552 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0978. Min Act: -0.0001

Data Index: 339265 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1018. Min Act: -0.0001

Data Index: 149845 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0978. Min Act: -0.0001

Data Index: 711027 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0931. Min Act: -0.0001

Data Index: 305757 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0989. Min Act: -0.0001

Data Index: 790806 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1298943 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1280240 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0946. Min Act: -0.0001

Data Index: 574858 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0870. Min Act: -0.0001

Data Index: 377579 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0895. Min Act: -0.0001

Data Index: 50506 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0901. Min Act: -0.0001

Data Index: 850090 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1186166 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1257935 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0876. Min Act: -0.0001

Data Index: 200185 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1205933 (C4 (Web Text))

Max Activating Token Index: 175