Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1340 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0006

Data Index: 802852 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0903. Min Act: -0.0006

Data Index: 842103 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0881. Min Act: -0.0006

Data Index: 838225 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0921. Min Act: -0.0006

Data Index: 960940 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0810. Min Act: -0.0006

Data Index: 1069516 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0908. Min Act: -0.0006

Data Index: 114024 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0908. Min Act: -0.0006

Data Index: 1239636 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0859. Min Act: -0.0006

Data Index: 1268840 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0858. Min Act: -0.0006

Data Index: 801607 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0888. Min Act: -0.0006

Data Index: 146577 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0853. Min Act: -0.0006

Data Index: 437548 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0818. Min Act: -0.0006

Data Index: 78099 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0850. Min Act: -0.0006

Data Index: 1178710 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0848. Min Act: -0.0006

Data Index: 6899 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0848. Min Act: -0.0005

Data Index: 499285 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0808. Min Act: -0.0006

Data Index: 223843 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0836. Min Act: -0.0006

Data Index: 162293 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0821. Min Act: -0.0006

Data Index: 423626 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0826. Min Act: -0.0006

Data Index: 333247 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0828. Min Act: -0.0006

Data Index: 604599 (C4 (Web Text))

Max Activating Token Index: 395