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

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

Neuron 1671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8869. Min Act: -0.0000

Data Index: 900259 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1568819 (Python Code)

Max Activating Token Index: 787

Text #2

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8043. Min Act: -0.0001

Data Index: 653149 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7851. Min Act: -0.0000

Data Index: 930988 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7147. Min Act: -0.0000

Data Index: 876244 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7439. Min Act: -0.0000

Data Index: 970357 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7084. Min Act: -0.0000

Data Index: 253440 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7350. Min Act: -0.0000

Data Index: 731858 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1557895 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1651728 (Python Code)

Max Activating Token Index: 399

Text #10

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7095. Min Act: -0.0000

Data Index: 747191 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6811. Min Act: -0.0000

Data Index: 534481 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1441029 (Python Code)

Max Activating Token Index: 648

Text #13

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1285957 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1034766 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1202445 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6811. Min Act: -0.0000

Data Index: 941953 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7472. Min Act: -0.0000

Data Index: 825620 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1233072 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1097776 (C4 (Web Text))

Max Activating Token Index: 210