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

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

Neuron 2139 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: 0.2293. Min Range: -0.2293

Max Act: 0.2293. Min Act: -0.0002

Data Index: 245978 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2159. Min Act: -0.0002

Data Index: 920959 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1988. Min Act: -0.0002

Data Index: 340776 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1999. Min Act: -0.0002

Data Index: 104936 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1757. Min Act: -0.0001

Data Index: 3730 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1940. Min Act: -0.0002

Data Index: 965319 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1945. Min Act: -0.0002

Data Index: 578294 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1861. Min Act: -0.0002

Data Index: 116046 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1827. Min Act: -0.0001

Data Index: 242559 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1766. Min Act: -0.0002

Data Index: 1047798 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1723. Min Act: -0.0002

Data Index: 338210 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1632. Min Act: -0.0002

Data Index: 540755 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1613. Min Act: -0.0001

Data Index: 187776 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1726. Min Act: -0.0001

Data Index: 861759 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1583. Min Act: -0.0001

Data Index: 432296 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1285779 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1572. Min Act: -0.0002

Data Index: 1136058 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1622. Min Act: -0.0002

Data Index: 77214 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1617. Min Act: -0.0002

Data Index: 325563 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1551. Min Act: -0.0001

Data Index: 500605 (C4 (Web Text))

Max Activating Token Index: 38