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

Dataset: The Pile

Neuron 3712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.6258. Min Act: -0.0000

Data Index: 621042 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1966806 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4837. Min Act: -0.0000

Data Index: 747256 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4984. Min Act: -0.0000

Data Index: 224705 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4761. Min Act: -0.0000

Data Index: 695755 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4921. Min Act: -0.0000

Data Index: 437951 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4906. Min Act: -0.0000

Data Index: 189831 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1854391 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1254296 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1178038 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4976. Min Act: -0.0000

Data Index: 6470 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1572209 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4426. Min Act: -0.0000

Data Index: 553785 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1623974 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1930010 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4445. Min Act: -0.0000

Data Index: 548621 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4845. Min Act: -0.0000

Data Index: 190914 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5226. Min Act: -0.0000

Data Index: 910238 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1897291 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4294. Min Act: -0.0000

Data Index: 126986 (The Pile)

Max Activating Token Index: 274