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

Dataset: The Pile

Neuron 2382 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.2584. Min Act: -0.0000

Data Index: 1066075 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.9946. Min Act: -0.0000

Data Index: 143725 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1134. Min Act: -0.0000

Data Index: 580355 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.9918. Min Act: -0.0000

Data Index: 1128101 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.8328. Min Act: -0.0000

Data Index: 454392 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.9293. Min Act: -0.0000

Data Index: 297078 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.6482. Min Act: -0.0000

Data Index: 816330 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0917. Min Act: -0.0000

Data Index: 946135 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0342. Min Act: -0.0000

Data Index: 1627347 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.7174. Min Act: -0.0000

Data Index: 328593 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.9044. Min Act: -0.0000

Data Index: 986605 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.6595. Min Act: -0.0000

Data Index: 578550 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.6392. Min Act: -0.0000

Data Index: 1526677 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.8550. Min Act: -0.0000

Data Index: 622251 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.8898. Min Act: -0.0000

Data Index: 1742971 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.6075. Min Act: -0.0000

Data Index: 64539 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.7103. Min Act: -0.0000

Data Index: 1760177 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.4049. Min Act: -0.0000

Data Index: 1772547 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.6173. Min Act: -0.0000

Data Index: 1853122 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 3.2584. Min Range: -3.2584

Max Act: 2.3810. Min Act: -0.0000

Data Index: 1874370 (The Pile)

Max Activating Token Index: 476