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

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

Neuron 2961 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.2577. Min Act: -0.0001

Data Index: 1144426 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.0371. Min Act: -0.0001

Data Index: 888367 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8637. Min Act: -0.0001

Data Index: 689466 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8338. Min Act: -0.0001

Data Index: 907207 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7729. Min Act: -0.0001

Data Index: 1225482 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8027. Min Act: -0.0001

Data Index: 364900 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8184. Min Act: -0.0001

Data Index: 555209 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8136. Min Act: -0.0001

Data Index: 1058000 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8369. Min Act: -0.0001

Data Index: 564419 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7878. Min Act: -0.0001

Data Index: 206196 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7580. Min Act: -0.0001

Data Index: 299964 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7414. Min Act: -0.0001

Data Index: 760739 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.6947. Min Act: -0.0001

Data Index: 592257 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1088428 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7321. Min Act: -0.0001

Data Index: 1167889 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7073. Min Act: -0.0001

Data Index: 1054763 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.6922. Min Act: -0.0001

Data Index: 853662 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.6977. Min Act: -0.0001

Data Index: 509991 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.6970. Min Act: -0.0001

Data Index: 1310371 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7142. Min Act: -0.0001

Data Index: 75148 (C4 (Web Text))

Max Activating Token Index: 135