Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6112 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.4841. Min Act: -0.0000

Data Index: 263026 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.3327. Min Act: -0.0000

Data Index: 944023 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.3272. Min Act: -0.0000

Data Index: 257237 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.3579. Min Act: -0.0000

Data Index: 685190 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.2585. Min Act: -0.0000

Data Index: 278065 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0556. Min Act: -0.0000

Data Index: 476720 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0823. Min Act: -0.0000

Data Index: 645470 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0617. Min Act: -0.0000

Data Index: 328581 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1087872 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0439. Min Act: -0.0000

Data Index: 500154 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1178691 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9652. Min Act: -0.0000

Data Index: 26045 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9632. Min Act: -0.0000

Data Index: 516612 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.8938. Min Act: 0.0000

Data Index: 1227491 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1077304 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.8947. Min Act: -0.0000

Data Index: 849688 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.8830. Min Act: -0.0000

Data Index: 848280 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1247104 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.8579. Min Act: -0.0000

Data Index: 263308 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.8481. Min Act: -0.0000

Data Index: 935969 (C4 (Web Text))

Max Activating Token Index: 810