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

Dataset: The Pile

Neuron 3416 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.1887. Min Act: -0.0000

Data Index: 986048 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.0499. Min Act: -0.0000

Data Index: 381769 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1518944 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1170228 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1156642 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1430776 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8776. Min Act: -0.0000

Data Index: 67518 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8361. Min Act: -0.0000

Data Index: 754927 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7965. Min Act: -0.0000

Data Index: 710694 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8421. Min Act: -0.0000

Data Index: 624650 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8120. Min Act: -0.0000

Data Index: 498069 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1985220 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1071578 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7667. Min Act: -0.0000

Data Index: 579853 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7814. Min Act: -0.0000

Data Index: 957360 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7793. Min Act: -0.0000

Data Index: 580244 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1066136 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7618. Min Act: -0.0000

Data Index: 144817 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7521. Min Act: -0.0000

Data Index: 189828 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1414312 (The Pile)

Max Activating Token Index: 83