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

Dataset: The Pile

Neuron 801 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.9106. Min Act: -0.0000

Data Index: 209054 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.7729. Min Act: -0.0000

Data Index: 239687 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.7502. Min Act: -0.0001

Data Index: 701582 (The Pile)

Max Activating Token Index: 200

Text #3

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.8456. Min Act: -0.0000

Data Index: 1777075 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.5546. Min Act: -0.0000

Data Index: 1679157 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.4928. Min Act: -0.0000

Data Index: 661253 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.4769. Min Act: -0.0000

Data Index: 813856 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1346599 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.5611. Min Act: -0.0000

Data Index: 507066 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.4428. Min Act: -0.0000

Data Index: 832212 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.4310. Min Act: -0.0000

Data Index: 1753917 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.3548. Min Act: -0.0000

Data Index: 728317 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.4209. Min Act: -0.0000

Data Index: 51113 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1340439 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.3881. Min Act: -0.0000

Data Index: 812243 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.3161. Min Act: -0.0000

Data Index: 747104 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1786195 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1302328 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1060374 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 1.9106. Min Range: -1.9106

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1279870 (The Pile)

Max Activating Token Index: 811