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

Dataset: The Pile

Neuron 2445 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1744402 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7589. Min Act: -0.0000

Data Index: 892576 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1170070 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1284149 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1903765 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1436649 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7166. Min Act: -0.0000

Data Index: 79176 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1656341 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7503. Min Act: -0.0000

Data Index: 737964 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7125. Min Act: -0.0000

Data Index: 648380 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6996. Min Act: -0.0000

Data Index: 336445 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1192755 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7135. Min Act: -0.0000

Data Index: 406950 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6739. Min Act: -0.0000

Data Index: 780530 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6953. Min Act: -0.0000

Data Index: 154429 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6520. Min Act: -0.0000

Data Index: 230812 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6219. Min Act: -0.0000

Data Index: 475157 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1090038 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6641. Min Act: -0.0000

Data Index: 663056 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6876. Min Act: -0.0000

Data Index: 897343 (The Pile)

Max Activating Token Index: 906