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

Dataset: The Pile

Neuron 4742 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.6203. Min Act: -0.0000

Data Index: 736033 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5534. Min Act: -0.0000

Data Index: 80622 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5242. Min Act: 0.0000

Data Index: 827081 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4915. Min Act: -0.0000

Data Index: 647349 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1120277 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4957. Min Act: 0.0000

Data Index: 1670629 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1290248 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4701. Min Act: 0.0000

Data Index: 1461665 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1471676 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4309. Min Act: -0.0000

Data Index: 991969 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4548. Min Act: -0.0000

Data Index: 210332 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4378. Min Act: 0.0000

Data Index: 803860 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1410542 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1424062 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4261. Min Act: -0.0000

Data Index: 380815 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4159. Min Act: 0.0000

Data Index: 1341218 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.3836. Min Act: 0.0000

Data Index: 1531215 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.3739. Min Act: -0.0000

Data Index: 429197 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.3974. Min Act: 0.0000

Data Index: 1929264 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1391864 (The Pile)

Max Activating Token Index: 452