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

Dataset: The Pile

Neuron 2590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3442. Min Act: -0.0003

Data Index: 1870080 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3224. Min Act: -0.0003

Data Index: 385298 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3437. Min Act: -0.0003

Data Index: 596975 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3098. Min Act: -0.0003

Data Index: 1438596 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3158. Min Act: -0.0003

Data Index: 206332 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3198. Min Act: -0.0003

Data Index: 1161952 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3133. Min Act: -0.0003

Data Index: 218371 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3140. Min Act: -0.0003

Data Index: 1578774 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2967. Min Act: -0.0003

Data Index: 1035229 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3000. Min Act: -0.0003

Data Index: 974298 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2868. Min Act: -0.0003

Data Index: 1862069 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2955. Min Act: -0.0003

Data Index: 1113056 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2841. Min Act: -0.0003

Data Index: 636770 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2915. Min Act: -0.0003

Data Index: 1458902 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3011. Min Act: -0.0003

Data Index: 1421611 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2879. Min Act: -0.0003

Data Index: 228308 (The Pile)

Max Activating Token Index: 220

Text #16

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2794. Min Act: -0.0003

Data Index: 336245 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2859. Min Act: -0.0003

Data Index: 1008559 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2868. Min Act: -0.0003

Data Index: 107802 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2752. Min Act: -0.0003

Data Index: 1512293 (The Pile)

Max Activating Token Index: 31