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

Dataset: The Pile

Neuron 1980 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: 3.1051. Min Range: -3.1051

Max Act: 3.1051. Min Act: -0.0000

Data Index: 1333165 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.7618. Min Act: -0.0000

Data Index: 982975 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.7577. Min Act: -0.0000

Data Index: 1301828 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.5667. Min Act: -0.0000

Data Index: 1041613 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.4921. Min Act: -0.0000

Data Index: 1237237 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.4970. Min Act: -0.0000

Data Index: 1319242 (The Pile)

Max Activating Token Index: 551

Text #6

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.6898. Min Act: -0.0000

Data Index: 1957042 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.5027. Min Act: -0.0000

Data Index: 1666016 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.3628. Min Act: -0.0000

Data Index: 1219253 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.3468. Min Act: -0.0000

Data Index: 1225367 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.2174. Min Act: -0.0000

Data Index: 1829320 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.4210. Min Act: -0.0000

Data Index: 175272 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.4372. Min Act: -0.0000

Data Index: 316339 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.2996. Min Act: -0.0000

Data Index: 513386 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 3.1051. Min Range: -3.1051

Max Act: 1.9757. Min Act: -0.0000

Data Index: 1309166 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.2910. Min Act: -0.0000

Data Index: 644886 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.1560. Min Act: -0.0000

Data Index: 1074476 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.2574. Min Act: -0.0000

Data Index: 1143494 (The Pile)

Max Activating Token Index: 429

Text #18

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.2483. Min Act: -0.0000

Data Index: 359318 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.2715. Min Act: -0.0000

Data Index: 1243562 (The Pile)

Max Activating Token Index: 560