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

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

Neuron 1592 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4990. Min Act: -0.0000

Data Index: 876861 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.2653. Min Act: -0.0000

Data Index: 682589 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.1758. Min Act: -0.0000

Data Index: 125747 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0980. Min Act: -0.0000

Data Index: 397718 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0328. Min Act: -0.0000

Data Index: 588893 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1012695 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0427. Min Act: -0.0000

Data Index: 765212 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0246. Min Act: -0.0000

Data Index: 993028 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0533. Min Act: -0.0000

Data Index: 596062 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1039167 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9215. Min Act: -0.0000

Data Index: 224245 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1099913 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0010. Min Act: -0.0000

Data Index: 640574 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1240078 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9993. Min Act: -0.0000

Data Index: 660340 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9884. Min Act: -0.0000

Data Index: 841153 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9594. Min Act: -0.0000

Data Index: 469689 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1214954 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9867. Min Act: -0.0000

Data Index: 488490 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.4990. Min Range: -1.4990

Max Act: 0.9655. Min Act: -0.0000

Data Index: 204249 (C4 (Web Text))

Max Activating Token Index: 989