Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4946 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.5157. Min Act: -0.0000

Data Index: 128557 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.4016. Min Act: -0.0000

Data Index: 957904 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.4090. Min Act: -0.0000

Data Index: 191498 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1023291 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0783. Min Act: -0.0000

Data Index: 654606 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1029826 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0718. Min Act: -0.0000

Data Index: 631163 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.9999. Min Act: -0.0000

Data Index: 930563 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.9605. Min Act: -0.0000

Data Index: 199579 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1198430 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1307540 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8793. Min Act: -0.0000

Data Index: 914477 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8449. Min Act: -0.0000

Data Index: 374707 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8382. Min Act: -0.0000

Data Index: 929000 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.9223. Min Act: -0.0000

Data Index: 824697 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1071659 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1022604 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1210925 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8291. Min Act: -0.0000

Data Index: 320134 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.8563. Min Act: -0.0000

Data Index: 357839 (C4 (Web Text))

Max Activating Token Index: 496