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

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

Neuron 3534 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1205578 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0151. Min Act: -0.0002

Data Index: 795366 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0149. Min Act: -0.0002

Data Index: 23184 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1089808 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0002

Data Index: 955990 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1085891 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1051635 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0002

Data Index: 738471 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0136. Min Act: -0.0002

Data Index: 925664 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 506203 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1409143 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1613191 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1496411 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1579205 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1412431 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1371365 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1563953 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 252704 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1008401 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0002

Data Index: 720632 (C4 (Web Text))

Max Activating Token Index: 1