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

Dataset: The Pile

Neuron 3690 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: 1.1669. Min Range: -1.1669

Max Act: 1.1669. Min Act: -0.0000

Data Index: 437181 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9875. Min Act: -0.0000

Data Index: 803804 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1266705 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1076969 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1333119 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1710262 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.7370. Min Act: -0.0000

Data Index: 757559 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1667910 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.6308. Min Act: -0.0000

Data Index: 235395 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1438099 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5980. Min Act: -0.0000

Data Index: 647978 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1669672 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.6363. Min Act: -0.0000

Data Index: 225607 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1285286 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5773. Min Act: -0.0000

Data Index: 198987 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5516. Min Act: -0.0000

Data Index: 292290 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5344. Min Act: -0.0000

Data Index: 910731 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5656. Min Act: -0.0000

Data Index: 319238 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5528. Min Act: -0.0000

Data Index: 408480 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1663921 (The Pile)

Max Activating Token Index: 431