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

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

Neuron 2785 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0001

Data Index: 531168 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1416312 (Python Code)

Max Activating Token Index: 992

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1345292 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1086913 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0143. Min Act: -0.0001

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1112198 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1638090 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0137. Min Act: -0.0001

Data Index: 1583192 (Python Code)

Max Activating Token Index: 617

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0120. Min Act: -0.0001

Data Index: 1632998 (Python Code)

Max Activating Token Index: 597

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0144. Min Act: -0.0001

Data Index: 1564500 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0128. Min Act: -0.0001

Data Index: 1608530 (Python Code)

Max Activating Token Index: 1021

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1542824 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1531067 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0142. Min Act: -0.0000

Data Index: 111076 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0133. Min Act: -0.0001

Data Index: 1651807 (Python Code)

Max Activating Token Index: 978

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1610302 (Python Code)

Max Activating Token Index: 958

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0131. Min Act: -0.0001

Data Index: 1066807 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0131. Min Act: -0.0001

Data Index: 1470125 (Python Code)

Max Activating Token Index: 961

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0133. Min Act: -0.0001

Data Index: 1631735 (Python Code)

Max Activating Token Index: 701

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1599949 (Python Code)

Max Activating Token Index: 798