Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2500 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0997. Min Act: -0.0001

Data Index: 414928 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1233982 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0924. Min Act: -0.0001

Data Index: 631994 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0985. Min Act: -0.0001

Data Index: 567534 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1322684 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0799. Min Act: -0.0001

Data Index: 907080 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1278991 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0775. Min Act: -0.0001

Data Index: 12146 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0823. Min Act: -0.0001

Data Index: 297961 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1267658 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0784. Min Act: -0.0001

Data Index: 969069 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0810. Min Act: -0.0001

Data Index: 918968 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0836. Min Act: -0.0001

Data Index: 704293 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0781. Min Act: -0.0001

Data Index: 220804 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0780. Min Act: -0.0001

Data Index: 713575 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1335827 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0788. Min Act: -0.0001

Data Index: 569233 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1292189 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0790. Min Act: -0.0001

Data Index: 380637 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0749. Min Act: -0.0001

Data Index: 104051 (C4 (Web Text))

Max Activating Token Index: 16