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

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

Neuron 2474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.9728. Min Act: -0.0000

Data Index: 1465558 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1078339 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.4221. Min Act: -0.0000

Data Index: 518215 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.4235. Min Act: -0.0000

Data Index: 979826 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.3083. Min Act: -0.0000

Data Index: 355112 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1575040 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2796. Min Act: -0.0000

Data Index: 1075764 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2399. Min Act: -0.0000

Data Index: 722592 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2061. Min Act: -0.0000

Data Index: 207649 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1379420 (Python Code)

Max Activating Token Index: 422

Text #10

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2956. Min Act: -0.0000

Data Index: 635888 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2066. Min Act: -0.0000

Data Index: 384954 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1351987 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.1632. Min Act: -0.0000

Data Index: 733319 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1578799 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2076. Min Act: -0.0000

Data Index: 835879 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1345696 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1293907 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.1972. Min Act: -0.0000

Data Index: 1317678 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.1644. Min Act: -0.0000

Data Index: 343631 (C4 (Web Text))

Max Activating Token Index: 532