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

Dataset: The Pile

Neuron 4955 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: 0.8976. Min Range: -0.8976

Max Act: 0.8937. Min Act: -0.0000

Data Index: 520947 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1421680 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1936832 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8012. Min Act: -0.0000

Data Index: 89266 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7832. Min Act: -0.0000

Data Index: 665965 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1410894 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7601. Min Act: -0.0000

Data Index: 447985 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7522. Min Act: -0.0000

Data Index: 248361 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7245. Min Act: -0.0000

Data Index: 47702 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1482698 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7205. Min Act: -0.0000

Data Index: 182244 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7615. Min Act: -0.0000

Data Index: 65551 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1594972 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1399502 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7093. Min Act: -0.0000

Data Index: 332262 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1368019 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1064351 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1165373 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7185. Min Act: -0.0000

Data Index: 239738 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1908548 (The Pile)

Max Activating Token Index: 785