Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 616 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.7179. Min Act: -0.0000

Data Index: 483288 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.5507. Min Act: -0.0001

Data Index: 839754 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.5771. Min Act: -0.0001

Data Index: 313346 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4520. Min Act: -0.0001

Data Index: 96061 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.3944. Min Act: -0.0000

Data Index: 687801 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4964. Min Act: -0.0001

Data Index: 140419 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4913. Min Act: -0.0000

Data Index: 970095 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.3828. Min Act: -0.0000

Data Index: 813747 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.5073. Min Act: -0.0001

Data Index: 40845 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4123. Min Act: -0.0000

Data Index: 456494 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.6909. Min Act: -0.0001

Data Index: 94311 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4094. Min Act: -0.0001

Data Index: 773720 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4105. Min Act: -0.0001

Data Index: 1584242 (Python Code)

Max Activating Token Index: 513

Text #13

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4135. Min Act: -0.0001

Data Index: 86485 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4434. Min Act: -0.0001

Data Index: 57978 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.3631. Min Act: -0.0001

Data Index: 504099 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.4648. Min Act: -0.0001

Data Index: 285486 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.3648. Min Act: -0.0001

Data Index: 1256574 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.3090. Min Act: -0.0000

Data Index: 62625 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.7179. Min Range: -1.7179

Max Act: 1.2571. Min Act: -0.0000

Data Index: 32878 (C4 (Web Text))

Max Activating Token Index: 767