Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3062 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.8404. Min Act: -0.0001

Data Index: 907727 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7049. Min Act: -0.0000

Data Index: 642982 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7490. Min Act: -0.0000

Data Index: 602815 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7005. Min Act: -0.0000

Data Index: 423875 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6429. Min Act: -0.0000

Data Index: 906828 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6163. Min Act: -0.0000

Data Index: 399153 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5985. Min Act: -0.0000

Data Index: 857162 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5964. Min Act: -0.0000

Data Index: 954358 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6094. Min Act: -0.0001

Data Index: 1326579 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1324440 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5839. Min Act: -0.0000

Data Index: 368485 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1324023 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1255584 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5291. Min Act: -0.0000

Data Index: 501849 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1290621 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1031863 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1245783 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1127476 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5465. Min Act: -0.0000

Data Index: 458009 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.5287. Min Act: -0.0000

Data Index: 293747 (C4 (Web Text))

Max Activating Token Index: 656