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

Dataset: The Pile

Neuron 1856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5365. Min Act: -0.0000

Data Index: 453179 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5314. Min Act: -0.0000

Data Index: 883974 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5104. Min Act: -0.0000

Data Index: 311518 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4522. Min Act: -0.0000

Data Index: 683766 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5418. Min Act: -0.0000

Data Index: 556447 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1093201 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5061. Min Act: -0.0000

Data Index: 117718 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5199. Min Act: -0.0000

Data Index: 90011 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1827535 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4846. Min Act: -0.0000

Data Index: 463841 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1490177 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4704. Min Act: -0.0000

Data Index: 138781 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4697. Min Act: -0.0000

Data Index: 362930 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4853. Min Act: -0.0000

Data Index: 213341 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1596703 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4782. Min Act: -0.0000

Data Index: 39747 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1883103 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1043068 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4715. Min Act: -0.0000

Data Index: 398207 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4861. Min Act: -0.0000

Data Index: 697032 (The Pile)

Max Activating Token Index: 881