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

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

Neuron 6046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.1018. Min Range: -9.1018

Max Act: 9.1018. Min Act: -0.0000

Data Index: 564583 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.8903. Min Act: -0.0000

Data Index: 866125 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.8769. Min Act: -0.0000

Data Index: 443622 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.5663. Min Act: -0.0000

Data Index: 447854 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.2388. Min Act: -0.0000

Data Index: 702208 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.7273. Min Act: -0.0000

Data Index: 10111 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.5427. Min Act: -0.0000

Data Index: 416286 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.5006. Min Act: -0.0000

Data Index: 399545 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.3050. Min Act: -0.0000

Data Index: 595764 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.2445. Min Act: -0.0000

Data Index: 772442 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.5895. Min Act: -0.0000

Data Index: 1143880 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.4055. Min Act: -0.0000

Data Index: 36762 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.4106. Min Act: -0.0000

Data Index: 486790 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.4122. Min Act: -0.0000

Data Index: 559785 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.5611. Min Act: -0.0000

Data Index: 1250641 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.3893. Min Act: -0.0000

Data Index: 879555 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.2313. Min Act: -0.0000

Data Index: 339459 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.5495. Min Act: -0.0000

Data Index: 210669 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.3654. Min Act: -0.0000

Data Index: 22964 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 9.1018. Min Range: -9.1018

Max Act: 8.5296. Min Act: -0.0000

Data Index: 809694 (C4 (Web Text))

Max Activating Token Index: 44