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

Dataset: The Pile

Neuron 3762 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: 0.4963. Min Range: -0.4963

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1746027 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1011401 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3708. Min Act: -0.0000

Data Index: 880432 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4443. Min Act: -0.0000

Data Index: 220255 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4479. Min Act: -0.0000

Data Index: 690792 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1078259 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1301114 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4711. Min Act: -0.0000

Data Index: 168591 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3746. Min Act: -0.0000

Data Index: 183257 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3772. Min Act: -0.0000

Data Index: 348988 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1182382 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3888. Min Act: -0.0000

Data Index: 976996 (The Pile)

Max Activating Token Index: 671

Text #12

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1575441 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1534729 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1672096 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1403881 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3391. Min Act: -0.0000

Data Index: 159592 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3409. Min Act: -0.0000

Data Index: 69865 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3219. Min Act: -0.0000

Data Index: 731086 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1561812 (The Pile)

Max Activating Token Index: 476