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

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

Neuron 2078 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1504529 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1109806 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1489982 (Python Code)

Max Activating Token Index: 376

Text #3

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3197. Min Act: -0.0000

Data Index: 985730 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1457227 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1588737 (Python Code)

Max Activating Token Index: 654

Text #6

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1445776 (Python Code)

Max Activating Token Index: 736

Text #7

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1649033 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1408297 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1537938 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1341740 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1621506 (Python Code)

Max Activating Token Index: 497

Text #12

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1025153 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1383516 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1434215 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1389381 (Python Code)

Max Activating Token Index: 865

Text #16

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1423332 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1107274 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2210. Min Act: -0.0000

Data Index: 542402 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2374. Min Act: -0.0000

Data Index: 599707 (C4 (Web Text))

Max Activating Token Index: 362