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

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

Neuron 1825 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1009180 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0001

Data Index: 697022 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1102200 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0823. Min Act: -0.0001

Data Index: 641720 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0832. Min Act: -0.0001

Data Index: 841588 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0771. Min Act: -0.0001

Data Index: 364972 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0905. Min Act: -0.0001

Data Index: 785791 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1169986 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0774. Min Act: -0.0001

Data Index: 221242 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0898. Min Act: -0.0001

Data Index: 998425 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0838. Min Act: -0.0001

Data Index: 328870 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1258307 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0934. Min Act: -0.0001

Data Index: 885803 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0882. Min Act: -0.0001

Data Index: 4793 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1148389 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0820. Min Act: -0.0001

Data Index: 934215 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0851. Min Act: -0.0001

Data Index: 299326 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0821. Min Act: -0.0001

Data Index: 251454 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1093346 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0804. Min Act: -0.0001

Data Index: 787292 (C4 (Web Text))

Max Activating Token Index: 468