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

Dataset: The Pile

Neuron 296 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: 1.5793. Min Range: -1.5793

Max Act: 1.5793. Min Act: -0.0000

Data Index: 78805 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4092. Min Act: -0.0000

Data Index: 735653 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3516. Min Act: -0.0000

Data Index: 901854 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4128. Min Act: -0.0000

Data Index: 428265 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1842121 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1897716 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4513. Min Act: -0.0000

Data Index: 1539394 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2809. Min Act: -0.0000

Data Index: 599223 (The Pile)

Max Activating Token Index: 144

Text #8

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3529. Min Act: -0.0000

Data Index: 276389 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1684545 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1684039 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3775. Min Act: -0.0000

Data Index: 1746376 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1325279 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1959501 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2851. Min Act: -0.0000

Data Index: 389133 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2826. Min Act: -0.0000

Data Index: 528911 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1856726 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.1784. Min Act: -0.0000

Data Index: 537426 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3164. Min Act: -0.0000

Data Index: 1646383 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2497. Min Act: -0.0000

Data Index: 441029 (The Pile)

Max Activating Token Index: 616