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

Dataset: The Pile

Neuron 4601 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2552. Min Range: -5.2552

Max Act: 5.2552. Min Act: -0.0000

Data Index: 1521873 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9017. Min Act: -0.0000

Data Index: 563714 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 5.2552. Min Range: -5.2552

Max Act: 5.0021. Min Act: -0.0000

Data Index: 937759 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9357. Min Act: -0.0000

Data Index: 1142921 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9573. Min Act: -0.0000

Data Index: 951196 (The Pile)

Max Activating Token Index: 536

Text #5

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9165. Min Act: -0.0000

Data Index: 1603241 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9077. Min Act: -0.0000

Data Index: 1122926 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.7112. Min Act: -0.0000

Data Index: 1830131 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8815. Min Act: -0.0000

Data Index: 785201 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8676. Min Act: -0.0000

Data Index: 57103 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.6891. Min Act: -0.0000

Data Index: 1185489 (The Pile)

Max Activating Token Index: 141

Text #11

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8480. Min Act: -0.0000

Data Index: 1273335 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.7917. Min Act: -0.0000

Data Index: 1793172 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.5858. Min Act: -0.0000

Data Index: 997852 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.7718. Min Act: -0.0000

Data Index: 1910804 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.5934. Min Act: -0.0000

Data Index: 871645 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.4051. Min Act: -0.0000

Data Index: 1169673 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.5657. Min Act: -0.0000

Data Index: 1918529 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.5728. Min Act: -0.0000

Data Index: 743338 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.7213. Min Act: -0.0000

Data Index: 329813 (The Pile)

Max Activating Token Index: 675