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

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

Neuron 5541 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: 2.7465. Min Range: -2.7465

Max Act: 2.7465. Min Act: -0.0000

Data Index: 572847 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.6599. Min Act: -0.0000

Data Index: 121042 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.4495. Min Act: -0.0000

Data Index: 290109 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.2527. Min Act: -0.0000

Data Index: 183061 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.9046. Min Act: -0.0000

Data Index: 401896 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.8789. Min Act: -0.0000

Data Index: 1261659 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.0090. Min Act: -0.0000

Data Index: 978020 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.0036. Min Act: -0.0000

Data Index: 781959 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.0964. Min Act: -0.0000

Data Index: 1124864 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.2010. Min Act: -0.0000

Data Index: 1336721 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.9341. Min Act: -0.0000

Data Index: 1227876 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 2.7465. Min Range: -2.7465

Max Act: 2.0337. Min Act: -0.0000

Data Index: 559184 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.8789. Min Act: -0.0000

Data Index: 1173108 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.7680. Min Act: -0.0000

Data Index: 1108634 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.8504. Min Act: -0.0001

Data Index: 953368 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.7445. Min Act: -0.0000

Data Index: 1206668 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.6513. Min Act: -0.0000

Data Index: 71564 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.8189. Min Act: -0.0000

Data Index: 623206 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.7078. Min Act: -0.0001

Data Index: 1014350 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 2.7465. Min Range: -2.7465

Max Act: 1.6705. Min Act: -0.0000

Data Index: 1054861 (C4 (Web Text))

Max Activating Token Index: 653