Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1966 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.5637. Min Act: -0.0002

Data Index: 227027 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3694. Min Act: -0.0002

Data Index: 947372 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.5196. Min Act: -0.0002

Data Index: 325643 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3465. Min Act: -0.0002

Data Index: 789157 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.4257. Min Act: -0.0002

Data Index: 901105 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.4065. Min Act: -0.0002

Data Index: 425964 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.4711. Min Act: -0.0002

Data Index: 365750 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3235. Min Act: -0.0002

Data Index: 951200 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3764. Min Act: -0.0002

Data Index: 1231659 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2833. Min Act: -0.0002

Data Index: 1104169 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3542. Min Act: -0.0002

Data Index: 909669 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3187. Min Act: -0.0002

Data Index: 1291645 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2875. Min Act: -0.0002

Data Index: 1249564 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3545. Min Act: -0.0002

Data Index: 974850 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3028. Min Act: -0.0002

Data Index: 921602 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2673. Min Act: -0.0002

Data Index: 1340134 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3142. Min Act: -0.0002

Data Index: 635595 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2301. Min Act: -0.0002

Data Index: 100330 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.1895. Min Act: -0.0001

Data Index: 31728 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3657. Min Act: -0.0002

Data Index: 7525 (C4 (Web Text))

Max Activating Token Index: 91