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

Dataset: The Pile

Neuron 3213 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: 0.2446. Min Range: -0.2446

Max Act: 0.2446. Min Act: -0.0000

Data Index: 109847 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2147. Min Act: -0.0000

Data Index: 813088 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2225. Min Act: -0.0000

Data Index: 159242 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1646631 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2051. Min Act: -0.0000

Data Index: 905488 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1912. Min Act: -0.0000

Data Index: 220518 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1971. Min Act: -0.0000

Data Index: 121599 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1500782 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1394776 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1901. Min Act: -0.0000

Data Index: 837644 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1082054 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1113056 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1093230 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1784. Min Act: 0.0000

Data Index: 1081374 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1603656 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1753. Min Act: 0.0000

Data Index: 108603 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1292125 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1572476 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1814. Min Act: -0.0000

Data Index: 919683 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1979117 (The Pile)

Max Activating Token Index: 105