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

Dataset: The Pile

Neuron 3300 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: 0.5377. Min Range: -0.5377

Max Act: 0.5014. Min Act: -0.0000

Data Index: 105336 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1765214 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1719508 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1814466 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3863. Min Act: -0.0000

Data Index: 594890 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1039948 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1667242 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1704034 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3528. Min Act: -0.0001

Data Index: 1041019 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1988100 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1989844 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1092565 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2791. Min Act: -0.0000

Data Index: 713051 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1112670 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2894. Min Act: -0.0001

Data Index: 354222 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1437152 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3137. Min Act: -0.0000

Data Index: 142143 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2991. Min Act: -0.0000

Data Index: 135037 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3167. Min Act: -0.0000

Data Index: 833912 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1584739 (The Pile)

Max Activating Token Index: 959