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

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

Neuron 4638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.6692. Min Act: -0.0000

Data Index: 123528 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.4617. Min Act: -0.0000

Data Index: 122092 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.3662. Min Act: -0.0000

Data Index: 364186 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.2990. Min Act: -0.0000

Data Index: 704715 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1348997 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.2293. Min Act: -0.0000

Data Index: 331781 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.2239. Min Act: -0.0000

Data Index: 721633 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1769. Min Act: -0.0000

Data Index: 955385 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1651. Min Act: -0.0000

Data Index: 645995 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.2360. Min Act: -0.0000

Data Index: 921168 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1778. Min Act: -0.0000

Data Index: 209703 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1086. Min Act: -0.0000

Data Index: 836520 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1395. Min Act: -0.0000

Data Index: 139699 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1722. Min Act: -0.0000

Data Index: 213789 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1609. Min Act: -0.0000

Data Index: 421095 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.2141. Min Act: -0.0000

Data Index: 649102 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0388. Min Act: -0.0000

Data Index: 199620 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0983. Min Act: -0.0000

Data Index: 140389 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1163493 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1511. Min Act: -0.0000

Data Index: 937283 (C4 (Web Text))

Max Activating Token Index: 76