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

Dataset: The Pile

Neuron 3268 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: 0.2673. Min Range: -0.2673

Max Act: 0.2319. Min Act: -0.0000

Data Index: 585565 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1339263 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2139. Min Act: -0.0000

Data Index: 904128 (The Pile)

Max Activating Token Index: 315

Text #3

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1521912 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1978. Min Act: -0.0000

Data Index: 52597 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1217508 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1407188 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1567140 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1176547 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1922. Min Act: -0.0000

Data Index: 990014 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1979. Min Act: -0.0000

Data Index: 381732 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1106120 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1283647 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1354169 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1856. Min Act: -0.0000

Data Index: 797757 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1897. Min Act: -0.0000

Data Index: 181416 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1845. Min Act: -0.0000

Data Index: 960663 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1349056 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1550860 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1951. Min Act: -0.0000

Data Index: 378744 (The Pile)

Max Activating Token Index: 426