Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1516346 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1752360 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.3120. Min Act: -0.0000

Data Index: 777602 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1356. Min Act: -0.0000

Data Index: 58466 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1269682 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1297089 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1986024 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0771. Min Act: -0.0000

Data Index: 140805 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1073. Min Act: -0.0000

Data Index: 775391 (The Pile)

Max Activating Token Index: 180

Text #9

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9004. Min Act: -0.0000

Data Index: 467957 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9998. Min Act: -0.0000

Data Index: 933155 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1721828 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.1342. Min Act: -0.0000

Data Index: 217364 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0174. Min Act: -0.0000

Data Index: 858143 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9791. Min Act: -0.0000

Data Index: 595915 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1000501 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1576779 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0233. Min Act: -0.0000

Data Index: 1362242 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 1.3127. Min Range: -1.3127

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1918815 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 1.3127. Min Range: -1.3127

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1594226 (The Pile)

Max Activating Token Index: 415