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

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

Neuron 299 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: 3.3657. Min Range: -3.3657

Max Act: 3.3657. Min Act: -0.0002

Data Index: 997205 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.8694. Min Act: -0.0002

Data Index: 92264 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.7093. Min Act: -0.0001

Data Index: 54092 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.5552. Min Act: -0.0001

Data Index: 234607 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.4927. Min Act: -0.0001

Data Index: 1060496 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.5751. Min Act: -0.0002

Data Index: 990316 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.8378. Min Act: -0.0002

Data Index: 661950 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.5344. Min Act: -0.0001

Data Index: 733994 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.5239. Min Act: -0.0001

Data Index: 276423 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.5114. Min Act: -0.0001

Data Index: 979999 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.4259. Min Act: -0.0002

Data Index: 640225 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.2468. Min Act: -0.0001

Data Index: 104343 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.1936. Min Act: -0.0002

Data Index: 1061417 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.4386. Min Act: -0.0002

Data Index: 383695 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.3150. Min Act: -0.0002

Data Index: 1232746 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.3933. Min Act: -0.0001

Data Index: 1320907 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.3582. Min Act: -0.0002

Data Index: 176804 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.2383. Min Act: -0.0001

Data Index: 1252933 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.2887. Min Act: -0.0001

Data Index: 479129 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.3661. Min Act: -0.0001

Data Index: 1012724 (C4 (Web Text))

Max Activating Token Index: 961