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

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

Neuron 4085 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0001

Data Index: 126294 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0802. Min Act: -0.0001

Data Index: 691687 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0767. Min Act: -0.0001

Data Index: 386187 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0745. Min Act: -0.0001

Data Index: 631475 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1050075 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0678. Min Act: -0.0001

Data Index: 706356 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0677. Min Act: -0.0001

Data Index: 144472 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0622. Min Act: -0.0001

Data Index: 686044 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1147697 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0603. Min Act: -0.0001

Data Index: 937605 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0595. Min Act: -0.0001

Data Index: 472612 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0635. Min Act: -0.0001

Data Index: 957773 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0661. Min Act: -0.0001

Data Index: 638542 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0636. Min Act: -0.0001

Data Index: 795263 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0648. Min Act: -0.0001

Data Index: 187031 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0597. Min Act: -0.0001

Data Index: 668576 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1255251 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0544. Min Act: -0.0001

Data Index: 761511 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0579. Min Act: -0.0001

Data Index: 731753 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1098072 (C4 (Web Text))

Max Activating Token Index: 323