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

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

Neuron 2235 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5595. Min Act: -0.0000

Data Index: 398682 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5480. Min Act: -0.0000

Data Index: 547281 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5275. Min Act: -0.0000

Data Index: 458408 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4802. Min Act: -0.0000

Data Index: 952408 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5109. Min Act: -0.0000

Data Index: 239190 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4526. Min Act: -0.0000

Data Index: 214519 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5312. Min Act: 0.0000

Data Index: 31712 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4779. Min Act: -0.0000

Data Index: 463219 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1356531 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4613. Min Act: -0.0000

Data Index: 68790 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4509. Min Act: -0.0000

Data Index: 239791 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4321. Min Act: -0.0000

Data Index: 513901 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4748. Min Act: -0.0000

Data Index: 310711 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4379. Min Act: -0.0000

Data Index: 39454 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1357759 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4323. Min Act: -0.0000

Data Index: 741883 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4186. Min Act: -0.0000

Data Index: 126293 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.3911. Min Act: -0.0000

Data Index: 786978 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4109. Min Act: -0.0000

Data Index: 670021 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.3972. Min Act: 0.0000

Data Index: 285349 (C4 (Web Text))

Max Activating Token Index: 543