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

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

Neuron 5774 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.5650. Min Act: -0.0000

Data Index: 369445 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.5428. Min Act: -0.0000

Data Index: 567364 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.3363. Min Act: -0.0000

Data Index: 794548 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.6084. Min Act: -0.0000

Data Index: 830826 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2613. Min Act: -0.0000

Data Index: 71124 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1776. Min Act: -0.0000

Data Index: 616217 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1656. Min Act: -0.0000

Data Index: 349635 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1564. Min Act: -0.0000

Data Index: 229427 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.0762. Min Act: -0.0000

Data Index: 1021527 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.0479. Min Act: -0.0000

Data Index: 547953 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.9030. Min Act: -0.0000

Data Index: 944359 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.8427. Min Act: -0.0000

Data Index: 667321 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.9868. Min Act: -0.0000

Data Index: 760804 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.9725. Min Act: -0.0000

Data Index: 1110498 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.6757. Min Act: -0.0000

Data Index: 594731 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.8097. Min Act: -0.0000

Data Index: 1230801 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.7492. Min Act: -0.0000

Data Index: 201105 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.6088. Min Act: -0.0000

Data Index: 1263770 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.0145. Min Act: -0.0000

Data Index: 885315 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 3.6084. Min Range: -3.6084

Max Act: 2.8377. Min Act: -0.0000

Data Index: 26524 (C4 (Web Text))

Max Activating Token Index: 1018