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

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

Neuron 1258 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.8713. Min Act: -0.0000

Data Index: 116015 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.9727. Min Act: -0.0000

Data Index: 712217 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.9080. Min Act: -0.0000

Data Index: 32614 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.7262. Min Act: -0.0000

Data Index: 619795 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5724. Min Act: -0.0000

Data Index: 63516 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5674. Min Act: -0.0000

Data Index: 1194535 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5265. Min Act: -0.0000

Data Index: 628347 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5321. Min Act: -0.0000

Data Index: 688427 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.6609. Min Act: -0.0000

Data Index: 1479770 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5264. Min Act: -0.0000

Data Index: 776671 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5022. Min Act: -0.0000

Data Index: 909098 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5102. Min Act: -0.0000

Data Index: 864109 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.3689. Min Act: -0.0000

Data Index: 1396456 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.4869. Min Act: -0.0000

Data Index: 359633 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.3317. Min Act: -0.0000

Data Index: 462245 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.4334. Min Act: -0.0000

Data Index: 869058 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5758. Min Act: -0.0000

Data Index: 73095 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.3091. Min Act: -0.0000

Data Index: 1398586 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.5463. Min Act: -0.0000

Data Index: 1384468 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 2.9727. Min Range: -2.9727

Max Act: 2.3947. Min Act: -0.0000

Data Index: 1654713 (Python Code)

Max Activating Token Index: 122