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

Dataset: The Pile

Neuron 841 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.4077. Min Act: -0.0000

Data Index: 107810 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3913. Min Act: -0.0000

Data Index: 581658 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1875667 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3251. Min Act: -0.0000

Data Index: 363137 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2120. Min Act: -0.0000

Data Index: 265925 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1609655 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3651. Min Act: -0.0000

Data Index: 1283831 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2581. Min Act: -0.0000

Data Index: 987997 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1924140 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2694. Min Act: -0.0000

Data Index: 42249 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3142. Min Act: -0.0000

Data Index: 11844 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1516671 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1688. Min Act: -0.0000

Data Index: 538849 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1714. Min Act: -0.0000

Data Index: 625185 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1871773 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1176358 (The Pile)

Max Activating Token Index: 893

Text #16

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1085150 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1605328 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1814. Min Act: -0.0000

Data Index: 368110 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1640. Min Act: 0.0000

Data Index: 1435290 (The Pile)

Max Activating Token Index: 262