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

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

Neuron 4118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8487. Min Act: -0.0002

Data Index: 1368987 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.9249. Min Act: -0.0002

Data Index: 1508105 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.9326. Min Act: -0.0002

Data Index: 93056 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 1.0736. Min Range: -1.0736

Max Act: 1.0736. Min Act: -0.0002

Data Index: 751739 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.9704. Min Act: -0.0002

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.9537. Min Act: -0.0002

Data Index: 230524 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8698. Min Act: -0.0002

Data Index: 1133075 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.9332. Min Act: -0.0002

Data Index: 942663 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.9049. Min Act: -0.0002

Data Index: 601757 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8999. Min Act: -0.0002

Data Index: 934511 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.0736. Min Range: -1.0736

Max Act: 1.0110. Min Act: -0.0002

Data Index: 1427272 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8697. Min Act: -0.0002

Data Index: 1168628 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8791. Min Act: -0.0002

Data Index: 676537 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8285. Min Act: -0.0002

Data Index: 1338016 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8074. Min Act: -0.0002

Data Index: 401298 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8535. Min Act: -0.0002

Data Index: 496075 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8498. Min Act: -0.0002

Data Index: 448642 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8163. Min Act: -0.0002

Data Index: 601670 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8729. Min Act: -0.0002

Data Index: 19780 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.0736. Min Range: -1.0736

Max Act: 0.8192. Min Act: -0.0002

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 389