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

Dataset: The Pile

Neuron 2161 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3641. Min Range: -5.3641

Max Act: 5.3641. Min Act: -0.0000

Data Index: 1108955 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 5.3641. Min Range: -5.3641

Max Act: 5.0696. Min Act: -0.0000

Data Index: 1029870 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.9253. Min Act: -0.0000

Data Index: 1852276 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.9671. Min Act: -0.0000

Data Index: 712322 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.8302. Min Act: -0.0000

Data Index: 1567147 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.5196. Min Act: -0.0000

Data Index: 384844 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.7003. Min Act: -0.0000

Data Index: 1145333 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.7134. Min Act: -0.0000

Data Index: 319228 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.2597. Min Act: -0.0000

Data Index: 1303596 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.4356. Min Act: -0.0000

Data Index: 1293005 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.2400. Min Act: -0.0000

Data Index: 726919 (The Pile)

Max Activating Token Index: 958

Text #11

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.1821. Min Act: -0.0000

Data Index: 257027 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.1992. Min Act: -0.0000

Data Index: 1373386 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.1530. Min Act: -0.0000

Data Index: 449625 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.1301. Min Act: -0.0000

Data Index: 382519 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.2353. Min Act: -0.0000

Data Index: 562714 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 5.3641. Min Range: -5.3641

Max Act: 3.9421. Min Act: -0.0000

Data Index: 1015064 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 5.3641. Min Range: -5.3641

Max Act: 3.7194. Min Act: -0.0000

Data Index: 1319870 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 5.3641. Min Range: -5.3641

Max Act: 4.1737. Min Act: -0.0000

Data Index: 1017336 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 5.3641. Min Range: -5.3641

Max Act: 3.8451. Min Act: -0.0000

Data Index: 1769271 (The Pile)

Max Activating Token Index: 946