Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1201 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2641. Min Act: -0.0001

Data Index: 552943 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2625. Min Act: -0.0001

Data Index: 70512 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1328147 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2140. Min Act: -0.0001

Data Index: 159958 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1963. Min Act: -0.0001

Data Index: 649145 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1939. Min Act: -0.0001

Data Index: 519759 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1207041 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1759. Min Act: -0.0001

Data Index: 216364 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1071617 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1769. Min Act: -0.0001

Data Index: 715955 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1835. Min Act: -0.0001

Data Index: 745057 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1728. Min Act: -0.0001

Data Index: 944459 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1714. Min Act: -0.0001

Data Index: 244116 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1209924 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1326666 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1202229 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1613. Min Act: -0.0001

Data Index: 813881 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1548. Min Act: -0.0001

Data Index: 917933 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1725. Min Act: -0.0001

Data Index: 818312 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1721. Min Act: -0.0001

Data Index: 149766 (C4 (Web Text))

Max Activating Token Index: 538