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

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

Neuron 1955 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: 1.3256. Min Range: -1.3256

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1312055 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0810. Min Act: -0.0000

Data Index: 174711 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0424. Min Act: -0.0000

Data Index: 298452 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0585. Min Act: -0.0000

Data Index: 688222 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9741. Min Act: -0.0000

Data Index: 303792 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9463. Min Act: -0.0000

Data Index: 221622 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9422. Min Act: -0.0000

Data Index: 724010 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1358378 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8823. Min Act: -0.0000

Data Index: 90249 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8782. Min Act: -0.0000

Data Index: 950720 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9175. Min Act: -0.0000

Data Index: 966738 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1124482 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8648. Min Act: -0.0000

Data Index: 190197 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8616. Min Act: -0.0000

Data Index: 916834 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8844. Min Act: -0.0000

Data Index: 197870 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8596. Min Act: -0.0000

Data Index: 71270 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8606. Min Act: -0.0000

Data Index: 646869 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8183. Min Act: -0.0000

Data Index: 410618 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8740. Min Act: -0.0000

Data Index: 697364 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8091. Min Act: -0.0000

Data Index: 369046 (C4 (Web Text))

Max Activating Token Index: 148