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

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

Neuron 2010 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.5060. Min Act: -0.0003

Data Index: 214546 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4782. Min Act: -0.0003

Data Index: 996622 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.5019. Min Act: -0.0003

Data Index: 188150 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4919. Min Act: -0.0002

Data Index: 153711 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4801. Min Act: -0.0003

Data Index: 521346 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4724. Min Act: -0.0003

Data Index: 769931 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4694. Min Act: -0.0003

Data Index: 1143298 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4771. Min Act: -0.0003

Data Index: 299960 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4462. Min Act: -0.0003

Data Index: 1271378 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4607. Min Act: -0.0002

Data Index: 1190670 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4669. Min Act: -0.0003

Data Index: 59517 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4365. Min Act: -0.0003

Data Index: 565838 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4409. Min Act: -0.0002

Data Index: 117265 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4281. Min Act: -0.0003

Data Index: 681209 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4283. Min Act: -0.0003

Data Index: 230907 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4321. Min Act: -0.0003

Data Index: 422011 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3805. Min Act: -0.0003

Data Index: 643013 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4444. Min Act: -0.0003

Data Index: 779157 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3973. Min Act: -0.0002

Data Index: 879053 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4253. Min Act: -0.0003

Data Index: 718453 (C4 (Web Text))

Max Activating Token Index: 146