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

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

Neuron 4097 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: 0.0148. Min Range: -0.0148

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1366433 (Python Code)

Max Activating Token Index: 664

Text #1

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1448822 (Python Code)

Max Activating Token Index: 899

Text #2

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1436196 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1486554 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1380248 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1616500 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1526570 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1608502 (Python Code)

Max Activating Token Index: 911

Text #8

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1455259 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1584166 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1571213 (Python Code)

Max Activating Token Index: 996

Text #11

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1502491 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1443148 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1520735 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1577180 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1645609 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1526435 (Python Code)

Max Activating Token Index: 770

Text #17

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1451680 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1603099 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1487068 (Python Code)

Max Activating Token Index: 989