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

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

Neuron 2685 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: 1.5961. Min Range: -1.5961

Max Act: 1.5961. Min Act: -0.0000

Data Index: 174651 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1107809 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3739. Min Act: -0.0000

Data Index: 574909 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.0925. Min Act: -0.0000

Data Index: 501164 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.0276. Min Act: -0.0000

Data Index: 178498 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.9034. Min Act: -0.0000

Data Index: 389787 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.8214. Min Act: -0.0000

Data Index: 811336 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1299336 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1235131 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.5036. Min Act: -0.0000

Data Index: 991345 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4654. Min Act: -0.0000

Data Index: 635741 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.5368. Min Act: -0.0000

Data Index: 302486 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1280007 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4848. Min Act: -0.0000

Data Index: 654219 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4827. Min Act: -0.0000

Data Index: 770386 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4894. Min Act: -0.0000

Data Index: 948800 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4534. Min Act: -0.0000

Data Index: 479008 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4377. Min Act: -0.0000

Data Index: 892940 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4434. Min Act: -0.0000

Data Index: 324351 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.5961. Min Range: -1.5961

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1295678 (C4 (Web Text))

Max Activating Token Index: 838