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

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

Neuron 2420 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0268. Min Range: -2.0268

Max Act: 2.0268. Min Act: -0.0000

Data Index: 896459 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1350500 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.4782. Min Act: -0.0000

Data Index: 687497 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1125013 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.4521. Min Act: -0.0000

Data Index: 374547 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.2758. Min Act: -0.0000

Data Index: 538410 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1330714 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.4155. Min Act: -0.0000

Data Index: 1011306 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.2183. Min Act: -0.0000

Data Index: 851662 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.2800. Min Act: -0.0000

Data Index: 479794 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.1769. Min Act: -0.0000

Data Index: 151453 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.1789. Min Act: -0.0000

Data Index: 175337 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1267115 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.1305. Min Act: -0.0000

Data Index: 157665 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.1100. Min Act: -0.0000

Data Index: 277534 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.0936. Min Act: -0.0000

Data Index: 159510 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.0957. Min Act: -0.0000

Data Index: 597644 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.0822. Min Act: -0.0000

Data Index: 323202 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1064138 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 2.0268. Min Range: -2.0268

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1182945 (C4 (Web Text))

Max Activating Token Index: 415