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

Dataset: The Pile

Neuron 161 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: 0.8741. Min Range: -0.8741

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1050102 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1163376 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.7846. Min Act: -0.0000

Data Index: 641576 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1945820 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.7262. Min Act: -0.0000

Data Index: 311904 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1325365 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6532. Min Act: -0.0000

Data Index: 442008 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1174826 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6529. Min Act: -0.0000

Data Index: 68356 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6601. Min Act: -0.0000

Data Index: 826937 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6215. Min Act: -0.0000

Data Index: 449960 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6144. Min Act: -0.0000

Data Index: 599381 (The Pile)

Max Activating Token Index: 234

Text #12

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1132061 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1526683 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5919. Min Act: -0.0000

Data Index: 960327 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1792063 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6086. Min Act: -0.0000

Data Index: 530661 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1788766 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1719836 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5789. Min Act: -0.0000

Data Index: 197459 (The Pile)

Max Activating Token Index: 150