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

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

Neuron 113 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: 2.1723. Min Range: -2.1723

Max Act: 2.1723. Min Act: -0.0000

Data Index: 1026774 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.9870. Min Act: -0.0000

Data Index: 871652 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.9520. Min Act: -0.0000

Data Index: 1299000 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.8511. Min Act: -0.0000

Data Index: 919817 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.6570. Min Act: -0.0000

Data Index: 288583 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.6091. Min Act: -0.0000

Data Index: 575981 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.5410. Min Act: -0.0000

Data Index: 180929 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.5518. Min Act: -0.0000

Data Index: 346441 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.4460. Min Act: -0.0000

Data Index: 558598 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.4027. Min Act: 0.0000

Data Index: 892122 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.5046. Min Act: -0.0000

Data Index: 653990 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.4185. Min Act: -0.0000

Data Index: 633990 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.4904. Min Act: -0.0000

Data Index: 675067 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1088731 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.4653. Min Act: -0.0000

Data Index: 413584 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.5375. Min Act: -0.0000

Data Index: 829729 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.4353. Min Act: -0.0000

Data Index: 259208 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.3395. Min Act: -0.0000

Data Index: 821921 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.4160. Min Act: -0.0000

Data Index: 998216 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 2.1723. Min Range: -2.1723

Max Act: 1.3435. Min Act: 0.0000

Data Index: 49155 (C4 (Web Text))

Max Activating Token Index: 714