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

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

Neuron 5416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1775. Min Act: -0.0000

Data Index: 324624 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1613. Min Act: -0.0000

Data Index: 1126942 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.9887. Min Act: -0.0000

Data Index: 388960 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8931. Min Act: -0.0000

Data Index: 836941 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.9896. Min Act: -0.0000

Data Index: 1353841 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.9116. Min Act: -0.0000

Data Index: 581749 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.7567. Min Act: -0.0000

Data Index: 454578 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8543. Min Act: -0.0000

Data Index: 1102291 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8484. Min Act: -0.0000

Data Index: 1118751 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8553. Min Act: -0.0000

Data Index: 426733 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.7541. Min Act: -0.0000

Data Index: 989043 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8431. Min Act: -0.0000

Data Index: 920940 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.9188. Min Act: -0.0000

Data Index: 398678 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8031. Min Act: -0.0000

Data Index: 314087 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8079. Min Act: -0.0000

Data Index: 338024 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.6923. Min Act: -0.0000

Data Index: 213597 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.7603. Min Act: -0.0000

Data Index: 678671 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.7026. Min Act: -0.0000

Data Index: 426859 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.7054. Min Act: -0.0000

Data Index: 735179 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.7042. Min Act: -0.0000

Data Index: 739285 (C4 (Web Text))

Max Activating Token Index: 553