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

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

Neuron 4373 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5295. Min Range: -2.5295

Max Act: 2.5295. Min Act: -0.0000

Data Index: 1048333 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 2.5295. Min Range: -2.5295

Max Act: 2.2632. Min Act: -0.0000

Data Index: 824971 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.5295. Min Range: -2.5295

Max Act: 2.2491. Min Act: -0.0000

Data Index: 58247 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.5295. Min Range: -2.5295

Max Act: 2.2416. Min Act: -0.0000

Data Index: 770472 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.8248. Min Act: -0.0000

Data Index: 1121683 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.9681. Min Act: -0.0000

Data Index: 89919 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.8192. Min Act: -0.0000

Data Index: 929825 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.8810. Min Act: -0.0000

Data Index: 755739 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1315164 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.8297. Min Act: -0.0000

Data Index: 878798 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.7809. Min Act: -0.0000

Data Index: 809475 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.7625. Min Act: -0.0000

Data Index: 531857 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.6661. Min Act: -0.0000

Data Index: 1215619 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.5292. Min Act: -0.0000

Data Index: 1346867 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.7997. Min Act: -0.0000

Data Index: 1128437 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.7094. Min Act: -0.0000

Data Index: 563768 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.7973. Min Act: -0.0000

Data Index: 1006828 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.6460. Min Act: -0.0000

Data Index: 420453 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.8013. Min Act: -0.0000

Data Index: 75980 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 2.5295. Min Range: -2.5295

Max Act: 1.6326. Min Act: -0.0000

Data Index: 1000149 (C4 (Web Text))

Max Activating Token Index: 480