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

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

Neuron 4272 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.9095. Min Act: -0.0000

Data Index: 58903 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1257883 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.3893. Min Act: -0.0000

Data Index: 327657 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.4011. Min Act: -0.0000

Data Index: 947302 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1554538 (Python Code)

Max Activating Token Index: 275

Text #5

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2949. Min Act: -0.0000

Data Index: 1198456 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1012272 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1055768 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1473389 (Python Code)

Max Activating Token Index: 389

Text #9

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0805. Min Act: -0.0000

Data Index: 126323 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.1458. Min Act: -0.0000

Data Index: 112773 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2084. Min Act: -0.0000

Data Index: 912709 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.1260. Min Act: -0.0000

Data Index: 345776 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1117820 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1489645 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1325707 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0538. Min Act: -0.0000

Data Index: 693090 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.9095. Min Range: -1.9095

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1496515 (Python Code)

Max Activating Token Index: 627

Text #18

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1414005 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1597532 (Python Code)

Max Activating Token Index: 28