Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2784 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.8841. Min Act: -0.0000

Data Index: 34930 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1206792 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.6167. Min Act: -0.0000

Data Index: 595969 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5970. Min Act: -0.0000

Data Index: 908010 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1088844 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1278901 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5543. Min Act: -0.0000

Data Index: 943772 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5488. Min Act: -0.0000

Data Index: 275882 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5513. Min Act: -0.0000

Data Index: 966815 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5472. Min Act: -0.0000

Data Index: 948425 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5338. Min Act: -0.0000

Data Index: 242950 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5096. Min Act: -0.0000

Data Index: 718931 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5014. Min Act: -0.0000

Data Index: 326426 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1016711 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5386. Min Act: -0.0000

Data Index: 46747 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1074195 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1100814 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5106. Min Act: -0.0001

Data Index: 305702 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.4899. Min Act: -0.0000

Data Index: 924909 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.8841. Min Range: -0.8841

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1288042 (C4 (Web Text))

Max Activating Token Index: 944