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

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

Neuron 4327 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.4168. Min Act: -0.0002

Data Index: 370042 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.4416. Min Act: -0.0002

Data Index: 101527 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.3878. Min Act: -0.0002

Data Index: 49736 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.3483. Min Act: -0.0002

Data Index: 1072375 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.3374. Min Act: -0.0002

Data Index: 247545 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.3238. Min Act: -0.0002

Data Index: 458601 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.3626. Min Act: -0.0002

Data Index: 1315410 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.2244. Min Act: -0.0002

Data Index: 595529 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.2787. Min Act: -0.0002

Data Index: 1211888 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.2242. Min Act: -0.0002

Data Index: 148793 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.2131. Min Act: -0.0002

Data Index: 103244 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.1873. Min Act: -0.0002

Data Index: 713707 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.2166. Min Act: -0.0002

Data Index: 538160 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.2250. Min Act: -0.0002

Data Index: 720893 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.1868. Min Act: -0.0002

Data Index: 1296838 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.1847. Min Act: -0.0003

Data Index: 543956 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.1125. Min Act: -0.0002

Data Index: 217914 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.1228. Min Act: -0.0002

Data Index: 1228517 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.1379. Min Act: -0.0002

Data Index: 919705 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.4416. Min Range: -1.4416

Max Act: 1.1778. Min Act: -0.0002

Data Index: 444504 (C4 (Web Text))

Max Activating Token Index: 726