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

Dataset: The Pile

Neuron 3816 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: 1.7129. Min Range: -1.7129

Max Act: 1.7129. Min Act: -0.0000

Data Index: 1189557 (The Pile)

Max Activating Token Index: 417

Text #1

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.5971. Min Act: -0.0000

Data Index: 455042 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.5935. Min Act: -0.0000

Data Index: 1131230 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.4223. Min Act: -0.0000

Data Index: 132034 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.3544. Min Act: -0.0000

Data Index: 336234 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.3509. Min Act: -0.0000

Data Index: 1691561 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.3073. Min Act: -0.0000

Data Index: 922967 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1696624 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1660640 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1894454 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1808910 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1751. Min Act: -0.0000

Data Index: 784108 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1248727 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1176. Min Act: -0.0000

Data Index: 967320 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1309208 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1128. Min Act: -0.0000

Data Index: 174282 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1056. Min Act: -0.0000

Data Index: 584140 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2414. Min Act: -0.0000

Data Index: 451331 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1119200 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.0000. Min Act: -0.0000

Data Index: 972228 (The Pile)

Max Activating Token Index: 973