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

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

Neuron 5040 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0486. Min Range: -1.0486

Max Act: 1.0486. Min Act: -0.0001

Data Index: 516047 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.9757. Min Act: -0.0001

Data Index: 1055610 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.9586. Min Act: -0.0001

Data Index: 473649 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.9323. Min Act: -0.0001

Data Index: 344613 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8806. Min Act: -0.0001

Data Index: 657614 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8797. Min Act: -0.0001

Data Index: 151199 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8621. Min Act: -0.0001

Data Index: 197866 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8528. Min Act: -0.0001

Data Index: 224603 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8355. Min Act: -0.0001

Data Index: 985224 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.7854. Min Act: -0.0001

Data Index: 1183025 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8313. Min Act: -0.0001

Data Index: 645278 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8313. Min Act: -0.0001

Data Index: 872856 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.7968. Min Act: -0.0001

Data Index: 534105 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.7940. Min Act: -0.0001

Data Index: 88955 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8421. Min Act: -0.0001

Data Index: 389820 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1324578 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.8019. Min Act: -0.0001

Data Index: 1265126 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.7486. Min Act: -0.0001

Data Index: 839667 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.7522. Min Act: -0.0001

Data Index: 1235698 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.0486. Min Range: -1.0486

Max Act: 0.7230. Min Act: -0.0001

Data Index: 291653 (C4 (Web Text))

Max Activating Token Index: 1003