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

Dataset: The Pile

Neuron 2888 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: 5.0661. Min Range: -5.0661

Max Act: 5.0661. Min Act: -0.0000

Data Index: 1668417 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 5.0661. Min Range: -5.0661

Max Act: 4.5896. Min Act: -0.0000

Data Index: 1578633 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 5.0661. Min Range: -5.0661

Max Act: 4.6090. Min Act: -0.0000

Data Index: 1284815 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.8801. Min Act: -0.0000

Data Index: 378932 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 5.0661. Min Range: -5.0661

Max Act: 4.0955. Min Act: -0.0000

Data Index: 1729705 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 5.0661. Min Range: -5.0661

Max Act: 4.0267. Min Act: -0.0000

Data Index: 756419 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.7276. Min Act: -0.0000

Data Index: 1030268 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.9697. Min Act: -0.0000

Data Index: 1999335 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 5.0661. Min Range: -5.0661

Max Act: 2.7716. Min Act: -0.0000

Data Index: 765885 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.1006. Min Act: -0.0000

Data Index: 1470124 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.2446. Min Act: -0.0000

Data Index: 1976319 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 5.0661. Min Range: -5.0661

Max Act: 4.0875. Min Act: -0.0000

Data Index: 941280 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.7877. Min Act: -0.0000

Data Index: 1638315 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.0595. Min Act: -0.0000

Data Index: 1415012 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.7063. Min Act: -0.0000

Data Index: 979098 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.7621. Min Act: -0.0000

Data Index: 338306 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.5787. Min Act: -0.0000

Data Index: 1998731 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.3082. Min Act: -0.0000

Data Index: 459788 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.2324. Min Act: -0.0000

Data Index: 1886437 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 5.0661. Min Range: -5.0661

Max Act: 3.9029. Min Act: -0.0000

Data Index: 484172 (The Pile)

Max Activating Token Index: 995