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

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

Neuron 3409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1603. Min Range: -2.1603

Max Act: 2.1603. Min Act: -0.0000

Data Index: 279949 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 2.1603. Min Range: -2.1603

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1301693 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.1603. Min Range: -2.1603

Max Act: 2.1072. Min Act: -0.0000

Data Index: 744570 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 2.1603. Min Range: -2.1603

Max Act: 2.0774. Min Act: -0.0000

Data Index: 1108631 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.8298. Min Act: -0.0000

Data Index: 277978 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.8091. Min Act: -0.0000

Data Index: 303129 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.7863. Min Act: -0.0000

Data Index: 1266248 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.8481. Min Act: -0.0000

Data Index: 180384 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.5858. Min Act: -0.0000

Data Index: 52782 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1349343 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.5073. Min Act: -0.0000

Data Index: 205245 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1043593 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4780. Min Act: -0.0000

Data Index: 754244 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1609867 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4484. Min Act: -0.0000

Data Index: 328821 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1057103 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4083. Min Act: -0.0000

Data Index: 57926 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4776. Min Act: -0.0000

Data Index: 882766 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.3583. Min Act: -0.0000

Data Index: 977044 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 2.1603. Min Range: -2.1603

Max Act: 1.4840. Min Act: -0.0000

Data Index: 384759 (C4 (Web Text))

Max Activating Token Index: 596