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

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

Neuron 749 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6993. Min Act: -0.0001

Data Index: 695378 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.7307. Min Act: -0.0001

Data Index: 1073202 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6878. Min Act: -0.0001

Data Index: 450578 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6658. Min Act: -0.0001

Data Index: 1072200 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6379. Min Act: -0.0001

Data Index: 1007643 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.7017. Min Act: -0.0001

Data Index: 227450 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6189. Min Act: -0.0001

Data Index: 596901 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6795. Min Act: -0.0001

Data Index: 620086 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6604. Min Act: -0.0001

Data Index: 138694 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.5946. Min Act: -0.0001

Data Index: 68618 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6613. Min Act: -0.0001

Data Index: 539407 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6380. Min Act: -0.0001

Data Index: 422457 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6767. Min Act: -0.0001

Data Index: 446107 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6332. Min Act: -0.0001

Data Index: 1023441 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6353. Min Act: -0.0001

Data Index: 215415 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6335. Min Act: -0.0001

Data Index: 455358 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6290. Min Act: -0.0001

Data Index: 870612 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6422. Min Act: -0.0001

Data Index: 599659 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.6024. Min Act: -0.0001

Data Index: 1039402 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.7307. Min Range: -0.7307

Max Act: 0.5744. Min Act: -0.0001

Data Index: 901786 (C4 (Web Text))

Max Activating Token Index: 383