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

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

Neuron 3928 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.9749. Min Act: -0.0001

Data Index: 1086034 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.8924. Min Act: -0.0001

Data Index: 462874 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.9143. Min Act: -0.0001

Data Index: 804507 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.0066. Min Range: -1.0066

Max Act: 1.0066. Min Act: -0.0001

Data Index: 1244758 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.8976. Min Act: -0.0002

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7601. Min Act: -0.0001

Data Index: 230223 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7100. Min Act: -0.0001

Data Index: 199659 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7701. Min Act: -0.0001

Data Index: 347934 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7488. Min Act: -0.0001

Data Index: 948528 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7647. Min Act: -0.0002

Data Index: 999609 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.6041. Min Act: -0.0002

Data Index: 947554 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.8287. Min Act: -0.0002

Data Index: 855047 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7454. Min Act: -0.0002

Data Index: 455425 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.6974. Min Act: -0.0002

Data Index: 630180 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.6150. Min Act: -0.0002

Data Index: 226014 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7022. Min Act: -0.0002

Data Index: 1175642 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7014. Min Act: -0.0001

Data Index: 1208028 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.6398. Min Act: -0.0001

Data Index: 26435 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.7201. Min Act: -0.0002

Data Index: 839027 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.0066. Min Range: -1.0066

Max Act: 0.6919. Min Act: -0.0002

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 904