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

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

Neuron 5789 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.6810. Min Act: -0.0000

Data Index: 526608 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.6847. Min Act: -0.0000

Data Index: 1437596 (Python Code)

Max Activating Token Index: 920

Text #2

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.4276. Min Act: -0.0000

Data Index: 782243 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1448368 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.2483. Min Act: -0.0000

Data Index: 666274 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.2469. Min Act: -0.0000

Data Index: 489406 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.0781. Min Act: -0.0000

Data Index: 248571 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.1086. Min Act: -0.0000

Data Index: 809197 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 1.6847. Min Range: -1.6847

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1086337 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.9084. Min Act: -0.0000

Data Index: 717743 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.9160. Min Act: -0.0000

Data Index: 22771 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1203707 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.8160. Min Act: -0.0000

Data Index: 407084 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1553336 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.7970. Min Act: -0.0000

Data Index: 403219 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1480906 (Python Code)

Max Activating Token Index: 400

Text #16

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1508203 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.7572. Min Act: -0.0000

Data Index: 978587 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1360812 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 1.6847. Min Range: -1.6847

Max Act: 0.7522. Min Act: -0.0000

Data Index: 996539 (C4 (Web Text))

Max Activating Token Index: 92