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

Dataset: The Pile

Neuron 2780 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: 3.0141. Min Range: -3.0141

Max Act: 3.0141. Min Act: -0.0000

Data Index: 1083106 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.2838. Min Act: -0.0000

Data Index: 488369 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.2789. Min Act: -0.0000

Data Index: 1747020 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.0578. Min Act: -0.0000

Data Index: 98122 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.2272. Min Act: -0.0000

Data Index: 40796 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.4346. Min Act: -0.0000

Data Index: 1813269 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.0544. Min Act: -0.0000

Data Index: 1961005 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.9563. Min Act: -0.0000

Data Index: 1608669 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.0437. Min Act: -0.0000

Data Index: 770355 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.0322. Min Act: -0.0000

Data Index: 621059 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 3.0141. Min Range: -3.0141

Max Act: 2.0977. Min Act: -0.0000

Data Index: 1083847 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.9477. Min Act: -0.0000

Data Index: 913724 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.9138. Min Act: -0.0000

Data Index: 1296296 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.9683. Min Act: -0.0000

Data Index: 1930043 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.8502. Min Act: -0.0000

Data Index: 1421747 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.9032. Min Act: -0.0000

Data Index: 1120150 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.8138. Min Act: -0.0000

Data Index: 1439629 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.6338. Min Act: -0.0000

Data Index: 929732 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.6409. Min Act: -0.0000

Data Index: 1496445 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 3.0141. Min Range: -3.0141

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1950915 (The Pile)

Max Activating Token Index: 920