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

Dataset: The Pile

Neuron 66 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: 0.9692. Min Range: -0.9692

Max Act: 0.9692. Min Act: -0.0000

Data Index: 191786 (The Pile)

Max Activating Token Index: 212

Text #1

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1430198 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7736. Min Act: -0.0000

Data Index: 749934 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1755519 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1107863 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6046. Min Act: -0.0000

Data Index: 561736 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6840. Min Act: 0.0000

Data Index: 1966043 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1442560 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6075. Min Act: -0.0000

Data Index: 209208 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6476. Min Act: -0.0000

Data Index: 995275 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6410. Min Act: -0.0000

Data Index: 495957 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6972. Min Act: -0.0000

Data Index: 604742 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1092778 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6460. Min Act: -0.0000

Data Index: 744302 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.5973. Min Act: -0.0000

Data Index: 397348 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6080. Min Act: -0.0000

Data Index: 17221 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1182532 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1746304 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1228415 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.5936. Min Act: -0.0000

Data Index: 579331 (The Pile)

Max Activating Token Index: 298