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

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

Neuron 3896 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.9558. Min Act: -0.0000

Data Index: 943521 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.8731. Min Act: -0.0000

Data Index: 672248 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7081. Min Act: -0.0000

Data Index: 613576 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6660. Min Act: -0.0000

Data Index: 57830 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1522274 (Python Code)

Max Activating Token Index: 611

Text #5

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1490901 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1579220 (Python Code)

Max Activating Token Index: 454

Text #7

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6338. Min Act: -0.0000

Data Index: 783475 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1477917 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1567473 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6771. Min Act: -0.0000

Data Index: 313134 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1413611 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6527. Min Act: -0.0000

Data Index: 341088 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1484890 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1487250 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1504328 (Python Code)

Max Activating Token Index: 253

Text #16

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1428319 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1620594 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5508. Min Act: -0.0000

Data Index: 241033 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1464177 (Python Code)

Max Activating Token Index: 536