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

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

Neuron 1313 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.1003. Min Act: -0.0001

Data Index: 631872 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0531. Min Act: -0.0000

Data Index: 746711 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9861. Min Act: -0.0001

Data Index: 660411 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9590. Min Act: -0.0001

Data Index: 180798 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0157. Min Act: -0.0001

Data Index: 61098 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9819. Min Act: -0.0001

Data Index: 251127 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1079009 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.8177. Min Act: -0.0001

Data Index: 269179 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.8066. Min Act: -0.0001

Data Index: 840164 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1519610 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1570426 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1022538 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7911. Min Act: -0.0001

Data Index: 271294 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7633. Min Act: -0.0000

Data Index: 930609 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.6686. Min Act: -0.0001

Data Index: 918655 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7371. Min Act: -0.0001

Data Index: 34750 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1426082 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7687. Min Act: -0.0000

Data Index: 917291 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7460. Min Act: -0.0001

Data Index: 486021 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.7647. Min Act: -0.0000

Data Index: 36617 (C4 (Web Text))

Max Activating Token Index: 808