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

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

Neuron 639 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: 1.6547. Min Range: -1.6547

Max Act: 1.6547. Min Act: -0.0000

Data Index: 38648 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1120617 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.3529. Min Act: -0.0000

Data Index: 261712 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.4985. Min Act: -0.0001

Data Index: 925794 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.4679. Min Act: -0.0000

Data Index: 601894 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.4007. Min Act: -0.0000

Data Index: 863517 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1082231 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.4160. Min Act: -0.0000

Data Index: 906892 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.4916. Min Act: -0.0000

Data Index: 56191 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.3748. Min Act: -0.0000

Data Index: 550781 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.3045. Min Act: -0.0000

Data Index: 331892 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.3391. Min Act: -0.0000

Data Index: 744537 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.4823. Min Act: -0.0000

Data Index: 30112 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.3116. Min Act: -0.0000

Data Index: 876215 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1065390 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.3008. Min Act: -0.0000

Data Index: 84223 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.3140. Min Act: -0.0000

Data Index: 1129381 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.1494. Min Act: -0.0000

Data Index: 822668 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.1438. Min Act: -0.0000

Data Index: 716558 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.6547. Min Range: -1.6547

Max Act: 1.0069. Min Act: -0.0001

Data Index: 1299568 (C4 (Web Text))

Max Activating Token Index: 169