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

Dataset: The Pile

Neuron 3428 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1965004 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1588139 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1593090 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8921. Min Act: -0.0000

Data Index: 459820 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1166819 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1768093 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8289. Min Act: -0.0000

Data Index: 47362 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8673. Min Act: -0.0000

Data Index: 928096 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1143727 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7995. Min Act: -0.0000

Data Index: 978284 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1987578 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.8067. Min Act: -0.0000

Data Index: 125496 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1829054 (The Pile)

Max Activating Token Index: 230

Text #13

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1024622 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7977. Min Act: -0.0000

Data Index: 476287 (The Pile)

Max Activating Token Index: 310

Text #15

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7930. Min Act: -0.0000

Data Index: 4109 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7355. Min Act: -0.0000

Data Index: 576987 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1054545 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1777954 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1739358 (The Pile)

Max Activating Token Index: 722