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

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

Neuron 5867 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.9313. Min Act: -0.0000

Data Index: 83409 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1096112 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.9162. Min Act: -0.0000

Data Index: 666579 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8445. Min Act: -0.0000

Data Index: 383477 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8125. Min Act: -0.0000

Data Index: 697415 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1070438 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8903. Min Act: -0.0000

Data Index: 75806 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1353962 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7829. Min Act: -0.0000

Data Index: 965736 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7427. Min Act: -0.0000

Data Index: 547765 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7191. Min Act: -0.0000

Data Index: 853788 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7333. Min Act: -0.0000

Data Index: 212707 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6939. Min Act: -0.0000

Data Index: 244935 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7292. Min Act: -0.0000

Data Index: 556295 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1059919 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7213. Min Act: -0.0000

Data Index: 600354 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7451. Min Act: -0.0000

Data Index: 815739 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7149. Min Act: -0.0000

Data Index: 459605 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7525. Min Act: -0.0000

Data Index: 633151 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6880. Min Act: -0.0000

Data Index: 310964 (C4 (Web Text))

Max Activating Token Index: 856