Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4050 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3646. Min Act: -0.0001

Data Index: 259498 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3180. Min Act: -0.0001

Data Index: 373565 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3047. Min Act: -0.0002

Data Index: 370488 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1872. Min Act: -0.0002

Data Index: 1259006 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0998. Min Act: -0.0001

Data Index: 268734 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0788. Min Act: -0.0001

Data Index: 424675 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0807. Min Act: -0.0001

Data Index: 14023 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1117. Min Act: -0.0002

Data Index: 355776 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1042. Min Act: -0.0002

Data Index: 673754 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0523. Min Act: -0.0001

Data Index: 424322 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0794. Min Act: -0.0002

Data Index: 218505 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0345. Min Act: -0.0001

Data Index: 932449 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0028. Min Act: -0.0001

Data Index: 782237 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9618. Min Act: -0.0001

Data Index: 1223398 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0719. Min Act: -0.0002

Data Index: 951804 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0134. Min Act: -0.0001

Data Index: 613447 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0360. Min Act: -0.0002

Data Index: 537329 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9760. Min Act: -0.0001

Data Index: 366671 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0514. Min Act: -0.0001

Data Index: 1033300 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9501. Min Act: -0.0001

Data Index: 719389 (C4 (Web Text))

Max Activating Token Index: 386