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

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

Neuron 1805 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: 2.7467. Min Range: -2.7467

Max Act: 2.7467. Min Act: -0.0000

Data Index: 410695 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.5515. Min Act: -0.0000

Data Index: 631479 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.4762. Min Act: -0.0000

Data Index: 295976 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.2795. Min Act: -0.0000

Data Index: 609367 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.5371. Min Act: -0.0000

Data Index: 634629 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.1056. Min Act: -0.0000

Data Index: 727422 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.3725. Min Act: -0.0000

Data Index: 846780 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.4903. Min Act: -0.0000

Data Index: 1200439 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.4481. Min Act: -0.0000

Data Index: 69767 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.2724. Min Act: -0.0000

Data Index: 722199 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.1154. Min Act: -0.0000

Data Index: 898077 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.1254. Min Act: -0.0000

Data Index: 432459 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.0969. Min Act: -0.0000

Data Index: 626966 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.2104. Min Act: -0.0000

Data Index: 155666 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.3552. Min Act: -0.0000

Data Index: 580369 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.0818. Min Act: -0.0000

Data Index: 1286446 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.1750. Min Act: -0.0000

Data Index: 1075236 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.1542. Min Act: -0.0000

Data Index: 3709 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.7467. Min Range: -2.7467

Max Act: 1.9472. Min Act: -0.0000

Data Index: 1336816 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.3183. Min Act: -0.0000

Data Index: 225192 (C4 (Web Text))

Max Activating Token Index: 636