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

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

Neuron 4680 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: 1.5999. Min Range: -1.5999

Max Act: 1.5999. Min Act: -0.0000

Data Index: 1088343 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1174283 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4020. Min Act: -0.0000

Data Index: 169773 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3586. Min Act: -0.0000

Data Index: 944688 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2073. Min Act: -0.0000

Data Index: 479596 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3047. Min Act: -0.0000

Data Index: 1347536 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1031076 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2158. Min Act: -0.0000

Data Index: 422357 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2829. Min Act: -0.0000

Data Index: 591386 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2122. Min Act: -0.0000

Data Index: 986780 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2342. Min Act: -0.0000

Data Index: 507648 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2565. Min Act: -0.0000

Data Index: 220972 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2649. Min Act: -0.0000

Data Index: 689736 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1237301 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.1325. Min Act: -0.0000

Data Index: 368282 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1012616 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2897. Min Act: -0.0000

Data Index: 532357 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1093195 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.1127. Min Act: -0.0000

Data Index: 68281 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.0809. Min Act: -0.0000

Data Index: 683446 (C4 (Web Text))

Max Activating Token Index: 77