Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 848 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.3152. Min Act: -0.0000

Data Index: 567931 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.6279. Min Act: -0.0000

Data Index: 920161 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.5582. Min Act: -0.0000

Data Index: 755566 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.1754. Min Act: -0.0000

Data Index: 501614 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.1477. Min Act: -0.0000

Data Index: 1031288 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.2052. Min Act: -0.0000

Data Index: 488581 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.0911. Min Act: -0.0000

Data Index: 1206019 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.1750. Min Act: -0.0000

Data Index: 932736 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 3.3152. Min Range: -3.3152

Max Act: 2.0428. Min Act: -0.0000

Data Index: 251095 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.9154. Min Act: -0.0000

Data Index: 430440 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.8740. Min Act: -0.0000

Data Index: 825650 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.9670. Min Act: -0.0000

Data Index: 766102 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.9237. Min Act: -0.0000

Data Index: 179445 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.8252. Min Act: -0.0000

Data Index: 384739 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.8162. Min Act: -0.0000

Data Index: 710063 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.8110. Min Act: -0.0000

Data Index: 749012 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.9649. Min Act: -0.0000

Data Index: 518077 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.8572. Min Act: -0.0000

Data Index: 522600 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.8493. Min Act: -0.0000

Data Index: 990954 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 3.3152. Min Range: -3.3152

Max Act: 1.8487. Min Act: -0.0000

Data Index: 967932 (C4 (Web Text))

Max Activating Token Index: 771