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

Dataset: The Pile

Neuron 1522 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: 0.0000

Data Index: 76577 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1558017 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1410. Min Act: 0.0000

Data Index: 568673 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1410. Min Act: 0.0000

Data Index: 922872 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1027880 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1213. Min Act: 0.0000

Data Index: 1110540 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1244. Min Act: 0.0000

Data Index: 1206502 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1198. Min Act: -0.0000

Data Index: 706039 (The Pile)

Max Activating Token Index: 12

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1580152 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: -0.0000

Data Index: 240782 (The Pile)

Max Activating Token Index: 3

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: 0.0000

Data Index: 879552 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: 0.0000

Data Index: 1027888 (The Pile)

Max Activating Token Index: 3

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: -0.0000

Data Index: 160776 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: 0.0000

Data Index: 1564193 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: 0.0000

Data Index: 1868384 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: -0.0000

Data Index: 587429 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1159. Min Act: 0.0000

Data Index: 718407 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1615959 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1130. Min Act: 0.0000

Data Index: 369932 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1297396 (The Pile)

Max Activating Token Index: 9