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

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

Neuron 3731 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.7717. Min Act: -0.0000

Data Index: 1025302 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.8271. Min Act: -0.0000

Data Index: 1088680 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5984. Min Act: -0.0000

Data Index: 824745 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.7183. Min Act: -0.0000

Data Index: 854758 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.7733. Min Act: -0.0000

Data Index: 1047954 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5701. Min Act: -0.0000

Data Index: 925789 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5755. Min Act: -0.0000

Data Index: 578703 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5408. Min Act: -0.0000

Data Index: 633656 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.4869. Min Act: -0.0000

Data Index: 187243 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3707. Min Act: -0.0000

Data Index: 516426 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1080187 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3540. Min Act: -0.0000

Data Index: 960334 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3341. Min Act: -0.0000

Data Index: 410027 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3621. Min Act: -0.0000

Data Index: 749383 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3684. Min Act: -0.0000

Data Index: 529463 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.4044. Min Act: -0.0000

Data Index: 726231 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3780. Min Act: -0.0000

Data Index: 531115 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3452. Min Act: -0.0000

Data Index: 647785 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.3464. Min Act: -0.0000

Data Index: 238743 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.2608. Min Act: -0.0000

Data Index: 134280 (C4 (Web Text))

Max Activating Token Index: 481