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

Dataset: The Pile

Neuron 822 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: 1.4178. Min Range: -1.4178

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1637093 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.4030. Min Act: -0.0000

Data Index: 738162 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1382159 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3543. Min Act: -0.0000

Data Index: 702164 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.4126. Min Act: -0.0000

Data Index: 1238283 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3797. Min Act: -0.0000

Data Index: 373767 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3465. Min Act: -0.0000

Data Index: 460955 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1918. Min Act: -0.0000

Data Index: 649257 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1573665 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1937016 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3057. Min Act: -0.0000

Data Index: 362548 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2702. Min Act: -0.0000

Data Index: 221192 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2068. Min Act: -0.0000

Data Index: 157424 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1796. Min Act: -0.0000

Data Index: 224945 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1475. Min Act: -0.0000

Data Index: 1043683 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2337. Min Act: -0.0000

Data Index: 601048 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.4178. Min Act: -0.0000

Data Index: 308874 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1417. Min Act: -0.0000

Data Index: 216437 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2105. Min Act: -0.0000

Data Index: 1052744 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1434801 (The Pile)

Max Activating Token Index: 417