Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2161 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.8841. Min Range: -3.8841

Max Act: 3.8841. Min Act: -0.0000

Data Index: 210208 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 3.8841. Min Range: -3.8841

Max Act: 2.6278. Min Act: -0.0000

Data Index: 1308000 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.8841. Min Range: -3.8841

Max Act: 2.3212. Min Act: -0.0000

Data Index: 26127 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 3.8841. Min Range: -3.8841

Max Act: 2.0787. Min Act: -0.0000

Data Index: 36712 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 3.8841. Min Range: -3.8841

Max Act: 2.0112. Min Act: -0.0000

Data Index: 667379 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 3.8841. Min Range: -3.8841

Max Act: 2.3270. Min Act: -0.0000

Data Index: 663394 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 3.8841. Min Range: -3.8841

Max Act: 2.0661. Min Act: -0.0000

Data Index: 997511 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 3.8841. Min Range: -3.8841

Max Act: 2.0731. Min Act: -0.0000

Data Index: 764438 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.7778. Min Act: -0.0000

Data Index: 714522 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.7346. Min Act: -0.0000

Data Index: 1122521 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.6837. Min Act: -0.0000

Data Index: 1353300 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.6800. Min Act: -0.0000

Data Index: 1110145 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1321530 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.7137. Min Act: -0.0000

Data Index: 539025 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.4832. Min Act: -0.0000

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.8468. Min Act: -0.0000

Data Index: 951787 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.4622. Min Act: -0.0000

Data Index: 1253454 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.8134. Min Act: -0.0000

Data Index: 721637 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.4748. Min Act: -0.0000

Data Index: 478208 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 3.8841. Min Range: -3.8841

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1321158 (C4 (Web Text))

Max Activating Token Index: 726