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

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

Neuron 2571 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4502. Min Act: -0.0000

Data Index: 714555 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4601. Min Act: -0.0000

Data Index: 632537 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4129. Min Act: -0.0000

Data Index: 318470 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4348. Min Act: -0.0000

Data Index: 142157 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4455. Min Act: -0.0000

Data Index: 640839 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4275. Min Act: -0.0000

Data Index: 510542 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3987. Min Act: -0.0000

Data Index: 916686 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4100. Min Act: -0.0000

Data Index: 582854 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4106. Min Act: -0.0000

Data Index: 164323 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4341. Min Act: -0.0000

Data Index: 176078 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4176. Min Act: -0.0000

Data Index: 267227 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1333682 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1007168 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1316148 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4176. Min Act: -0.0000

Data Index: 586251 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1080411 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1646184 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3980. Min Act: -0.0000

Data Index: 882204 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1219022 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4235. Min Act: -0.0000

Data Index: 901134 (C4 (Web Text))

Max Activating Token Index: 360