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

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

Neuron 1325 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1526313 (Python Code)

Max Activating Token Index: 754

Text #1

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1583089 (Python Code)

Max Activating Token Index: 846

Text #2

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1649775 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1560268 (Python Code)

Max Activating Token Index: 472

Text #4

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.6892. Min Act: -0.0000

Data Index: 326937 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1580834 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1373585 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1147494 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5997. Min Act: -0.0000

Data Index: 545589 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5974. Min Act: -0.0000

Data Index: 727983 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1612472 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1252708 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1654773 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1612044 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1648334 (Python Code)

Max Activating Token Index: 733

Text #15

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5471. Min Act: -0.0000

Data Index: 102894 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1145089 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5815. Min Act: -0.0000

Data Index: 985082 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1614212 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.8190. Min Range: -0.8190

Max Act: 0.5467. Min Act: -0.0000

Data Index: 677401 (C4 (Web Text))

Max Activating Token Index: 502