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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.8081. Min Act: -0.0000

Data Index: 300758 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6525. Min Act: -0.0000

Data Index: 933112 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1032904 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1250266 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6174. Min Act: -0.0000

Data Index: 393972 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5937. Min Act: -0.0000

Data Index: 360392 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6110. Min Act: -0.0000

Data Index: 130933 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5676. Min Act: -0.0000

Data Index: 396392 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5837. Min Act: -0.0000

Data Index: 991785 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5838. Min Act: -0.0000

Data Index: 583686 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1257938 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5688. Min Act: -0.0000

Data Index: 339778 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1090276 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5523. Min Act: -0.0000

Data Index: 487136 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1011562 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5586. Min Act: -0.0000

Data Index: 930214 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5783. Min Act: -0.0000

Data Index: 975364 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5560. Min Act: -0.0000

Data Index: 718300 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1280351 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5151. Min Act: -0.0000

Data Index: 214481 (C4 (Web Text))

Max Activating Token Index: 200