Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3322 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.6533. Min Act: -0.0001

Data Index: 409359 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.3242. Min Act: -0.0000

Data Index: 372785 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.3189. Min Act: -0.0000

Data Index: 503073 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.2438. Min Act: -0.0000

Data Index: 443753 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.1667. Min Act: -0.0000

Data Index: 767909 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.1536. Min Act: -0.0000

Data Index: 933064 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.1480. Min Act: -0.0001

Data Index: 935646 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1135649 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.2237. Min Act: -0.0000

Data Index: 74866 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.1106. Min Act: -0.0000

Data Index: 359383 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0470. Min Act: -0.0000

Data Index: 587821 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1244377 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0710. Min Act: -0.0001

Data Index: 417087 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0304. Min Act: -0.0000

Data Index: 904937 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0446. Min Act: -0.0000

Data Index: 391623 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0516. Min Act: -0.0000

Data Index: 361101 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0310. Min Act: -0.0000

Data Index: 633453 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.9888. Min Act: -0.0000

Data Index: 74271 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0591. Min Act: -0.0001

Data Index: 881556 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.9749. Min Act: -0.0001

Data Index: 639982 (C4 (Web Text))

Max Activating Token Index: 513