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

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

Neuron 4667 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1100. Min Act: -0.0002

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1094. Min Act: -0.0002

Data Index: 191097 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0981. Min Act: -0.0002

Data Index: 832058 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1050712 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0873. Min Act: -0.0002

Data Index: 304982 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0880. Min Act: -0.0002

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1250113 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0729. Min Act: -0.0002

Data Index: 106874 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0705. Min Act: -0.0002

Data Index: 51221 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0658. Min Act: -0.0002

Data Index: 926889 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0557. Min Act: -0.0002

Data Index: 522284 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0571. Min Act: -0.0002

Data Index: 759165 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1386998 (Python Code)

Max Activating Token Index: 636

Text #13

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1579451 (Python Code)

Max Activating Token Index: 679

Text #14

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0461. Min Act: -0.0002

Data Index: 831560 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1508531 (Python Code)

Max Activating Token Index: 434

Text #16

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0491. Min Act: -0.0002

Data Index: 49177 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0508. Min Act: -0.0002

Data Index: 701010 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0503. Min Act: -0.0002

Data Index: 504058 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1619221 (Python Code)

Max Activating Token Index: 451