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

Dataset: The Pile

Neuron 1191 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: 1.5721. Min Range: -1.5721

Max Act: 1.5721. Min Act: -0.0000

Data Index: 374870 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.3824. Min Act: -0.0000

Data Index: 1275975 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.3564. Min Act: -0.0000

Data Index: 230173 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1637962 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1003318 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.0654. Min Act: -0.0000

Data Index: 954361 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.9795. Min Act: -0.0000

Data Index: 602186 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1689621 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1007707 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.8879. Min Act: -0.0000

Data Index: 948345 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1724979 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.8577. Min Act: -0.0000

Data Index: 953162 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.9019. Min Act: -0.0001

Data Index: 42867 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.8306. Min Act: -0.0000

Data Index: 370275 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.7908. Min Act: -0.0000

Data Index: 36173 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1979924 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.7986. Min Act: -0.0000

Data Index: 763073 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.8207. Min Act: -0.0000

Data Index: 824640 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.8368. Min Act: -0.0000

Data Index: 885453 (The Pile)

Max Activating Token Index: 107

Text #19

Max Range: 1.5721. Min Range: -1.5721

Max Act: 0.7491. Min Act: -0.0000

Data Index: 868764 (The Pile)

Max Activating Token Index: 678