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

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

Neuron 1817 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.8944. Min Act: -0.0000

Data Index: 143604 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.6365. Min Act: -0.0000

Data Index: 61955 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.3540. Min Act: -0.0000

Data Index: 207632 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.5124. Min Act: -0.0000

Data Index: 22020 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4948. Min Act: -0.0000

Data Index: 833824 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1069127 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1966. Min Act: -0.0000

Data Index: 98617 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2472. Min Act: -0.0000

Data Index: 964424 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2914. Min Act: -0.0000

Data Index: 26647 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2172. Min Act: -0.0000

Data Index: 820925 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1904. Min Act: -0.0000

Data Index: 97315 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1233340 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.0380. Min Act: -0.0000

Data Index: 951447 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1383957 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1107331 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1542441 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1077365 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1809. Min Act: -0.0000

Data Index: 662222 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1020. Min Act: -0.0000

Data Index: 904815 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1027531 (C4 (Web Text))

Max Activating Token Index: 939