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

Dataset: The Pile

Neuron 1558 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.2197. Min Act: -0.0000

Data Index: 818016 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0421. Min Act: -0.0000

Data Index: 861291 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0404. Min Act: -0.0000

Data Index: 1409787 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0862. Min Act: -0.0000

Data Index: 176974 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0770. Min Act: -0.0000

Data Index: 417062 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9569. Min Act: -0.0000

Data Index: 90653 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9472. Min Act: -0.0000

Data Index: 341963 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0252. Min Act: -0.0000

Data Index: 560616 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9310. Min Act: -0.0000

Data Index: 435170 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9915. Min Act: -0.0000

Data Index: 727875 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.8991. Min Act: -0.0000

Data Index: 932538 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0239. Min Act: -0.0000

Data Index: 625614 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0003. Min Act: -0.0000

Data Index: 907586 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9104. Min Act: -0.0000

Data Index: 277896 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.8543. Min Act: -0.0000

Data Index: 309437 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9826. Min Act: -0.0000

Data Index: 158856 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9152. Min Act: -0.0000

Data Index: 717532 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1871997 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1615225 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9076. Min Act: -0.0000

Data Index: 203002 (The Pile)

Max Activating Token Index: 636