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

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

Neuron 1497 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: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0001

Data Index: 1522223 (Python Code)

Max Activating Token Index: 455

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1527245 (Python Code)

Max Activating Token Index: 448

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1482535 (Python Code)

Max Activating Token Index: 470

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2459. Min Act: -0.0001

Data Index: 1554835 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1600478 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2354. Min Act: -0.0001

Data Index: 171863 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1544364 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1040619 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2211. Min Act: -0.0001

Data Index: 569191 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2017. Min Act: -0.0001

Data Index: 425067 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1888. Min Act: -0.0001

Data Index: 576237 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1435518 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1328675 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2132. Min Act: -0.0001

Data Index: 345777 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2009. Min Act: -0.0001

Data Index: 1084664 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1826. Min Act: -0.0001

Data Index: 41362 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1924. Min Act: -0.0001

Data Index: 28864 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1802. Min Act: -0.0001

Data Index: 876790 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1936. Min Act: -0.0002

Data Index: 696594 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1449. Min Act: -0.0001

Data Index: 342975 (C4 (Web Text))

Max Activating Token Index: 270