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

Dataset: The Pile

Neuron 3899 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: 2.4698. Min Range: -2.4698

Max Act: 2.4698. Min Act: -0.0000

Data Index: 653437 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.3092. Min Act: -0.0000

Data Index: 897603 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.2715. Min Act: -0.0000

Data Index: 633141 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.1699. Min Act: -0.0000

Data Index: 113389 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.1808. Min Act: -0.0000

Data Index: 964140 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.0156. Min Act: -0.0000

Data Index: 930601 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.9251. Min Act: -0.0000

Data Index: 1525547 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.0170. Min Act: -0.0000

Data Index: 454076 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1427428 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.8914. Min Act: -0.0000

Data Index: 235259 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 2.4698. Min Range: -2.4698

Max Act: 2.0739. Min Act: -0.0000

Data Index: 1029795 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1821217 (The Pile)

Max Activating Token Index: 185

Text #12

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.9053. Min Act: -0.0000

Data Index: 1156780 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.8545. Min Act: -0.0000

Data Index: 1016992 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.8109. Min Act: -0.0000

Data Index: 1609751 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.9069. Min Act: -0.0000

Data Index: 1243219 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.8969. Min Act: -0.0000

Data Index: 512962 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.6947. Min Act: -0.0000

Data Index: 635179 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1763226 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 2.4698. Min Range: -2.4698

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1834787 (The Pile)

Max Activating Token Index: 398