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

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

Neuron 4554 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.5441. Min Act: -0.0000

Data Index: 386973 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.5751. Min Act: -0.0000

Data Index: 602767 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.5417. Min Act: -0.0000

Data Index: 775296 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.5136. Min Act: -0.0000

Data Index: 27544 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4589. Min Act: 0.0000

Data Index: 21542 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4650. Min Act: -0.0000

Data Index: 114923 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1145736 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4379. Min Act: -0.0000

Data Index: 731130 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4499. Min Act: -0.0000

Data Index: 614677 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4152. Min Act: -0.0000

Data Index: 136815 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4072. Min Act: -0.0000

Data Index: 341817 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4214. Min Act: -0.0000

Data Index: 455070 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1099817 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.3993. Min Act: -0.0000

Data Index: 792476 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1308941 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1301514 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4153. Min Act: 0.0001

Data Index: 1269757 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4105. Min Act: -0.0000

Data Index: 106277 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.3988. Min Act: -0.0000

Data Index: 378111 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.3857. Min Act: 0.0000

Data Index: 410971 (C4 (Web Text))

Max Activating Token Index: 750