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

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

Neuron 4536 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0124. Min Act: -0.0000

Data Index: 423516 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0000

Data Index: 678343 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0000

Data Index: 454751 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0000

Data Index: 669236 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1148576 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0092. Min Act: -0.0000

Data Index: 502241 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0091. Min Act: -0.0000

Data Index: 848806 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0081. Min Act: -0.0000

Data Index: 693702 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0088. Min Act: -0.0000

Data Index: 1101995 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1257915 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0077. Min Act: -0.0000

Data Index: 590489 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0081. Min Act: -0.0000

Data Index: 620900 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0077. Min Act: -0.0000

Data Index: 384776 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0081. Min Act: -0.0000

Data Index: 471565 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0077. Min Act: -0.0000

Data Index: 804764 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0075. Min Act: -0.0000

Data Index: 265868 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0073. Min Act: -0.0000

Data Index: 1327054 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0075. Min Act: -0.0000

Data Index: 476590 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0073. Min Act: -0.0000

Data Index: 1389811 (Python Code)

Max Activating Token Index: 965

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0075. Min Act: -0.0000

Data Index: 1111329 (C4 (Web Text))

Max Activating Token Index: 1019