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

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

Neuron 3543 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.8939. Min Act: -0.0000

Data Index: 141946 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.9775. Min Act: -0.0000

Data Index: 1337514 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.8534. Min Act: -0.0001

Data Index: 745848 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.7819. Min Act: -0.0000

Data Index: 4050 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.6907. Min Act: -0.0000

Data Index: 662778 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.5322. Min Act: -0.0000

Data Index: 988854 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.5791. Min Act: -0.0000

Data Index: 906686 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.5593. Min Act: -0.0000

Data Index: 335457 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.7034. Min Act: -0.0000

Data Index: 662620 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.4972. Min Act: -0.0000

Data Index: 493687 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.4423. Min Act: -0.0001

Data Index: 1349713 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.3943. Min Act: -0.0000

Data Index: 725457 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.3803. Min Act: -0.0000

Data Index: 3401 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.4631. Min Act: -0.0000

Data Index: 215787 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.3465. Min Act: -0.0000

Data Index: 454047 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.3769. Min Act: -0.0001

Data Index: 1185352 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.4626. Min Act: -0.0001

Data Index: 1294015 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.3625. Min Act: -0.0000

Data Index: 205095 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.3508. Min Act: -0.0000

Data Index: 258040 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.9775. Min Range: -1.9775

Max Act: 1.2966. Min Act: -0.0001

Data Index: 600064 (C4 (Web Text))

Max Activating Token Index: 344