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

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

Neuron 1331 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: 1.6379. Min Range: -1.6379

Max Act: 1.6379. Min Act: -0.0000

Data Index: 1081292 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.3906. Min Act: -0.0000

Data Index: 504424 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1159091 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1728. Min Act: -0.0000

Data Index: 883924 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1289179 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1603. Min Act: -0.0000

Data Index: 528637 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1236854 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1151398 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0680. Min Act: -0.0000

Data Index: 488810 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 1.6379. Min Range: -1.6379

Max Act: 0.9818. Min Act: -0.0000

Data Index: 773939 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 1.6379. Min Range: -1.6379

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1160614 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 1.6379. Min Range: -1.6379

Max Act: 0.9819. Min Act: -0.0000

Data Index: 575442 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0224. Min Act: -0.0000

Data Index: 332555 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1212154 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1492703 (Python Code)

Max Activating Token Index: 872

Text #15

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0336. Min Act: -0.0000

Data Index: 663418 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0300. Min Act: -0.0000

Data Index: 203257 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0651. Min Act: -0.0000

Data Index: 30931 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0851. Min Act: -0.0000

Data Index: 396374 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 1.6379. Min Range: -1.6379

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1252584 (C4 (Web Text))

Max Activating Token Index: 613