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

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

Neuron 1011 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: 0.5677. Min Range: -0.5677

Max Act: 0.5677. Min Act: -0.0000

Data Index: 648595 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1255423 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1175233 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4888. Min Act: -0.0000

Data Index: 152720 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4679. Min Act: -0.0000

Data Index: 524411 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4673. Min Act: -0.0000

Data Index: 15382 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4780. Min Act: -0.0000

Data Index: 397005 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4656. Min Act: -0.0000

Data Index: 990840 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4520. Min Act: -0.0000

Data Index: 492103 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4304. Min Act: -0.0000

Data Index: 896382 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1098518 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4383. Min Act: -0.0000

Data Index: 162350 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1092105 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4113. Min Act: -0.0000

Data Index: 11294 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1351609 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4080. Min Act: -0.0000

Data Index: 551063 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3648. Min Act: -0.0000

Data Index: 183074 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3767. Min Act: -0.0000

Data Index: 71886 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3524. Min Act: -0.0000

Data Index: 588747 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3615. Min Act: -0.0000

Data Index: 614567 (C4 (Web Text))

Max Activating Token Index: 576