Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1650 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1101. Min Act: -0.0002

Data Index: 440648 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1030084 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1112606 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1094. Min Act: -0.0002

Data Index: 247224 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1041. Min Act: -0.0002

Data Index: 626258 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0906. Min Act: -0.0002

Data Index: 373082 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0950. Min Act: -0.0001

Data Index: 399591 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0926. Min Act: -0.0002

Data Index: 66721 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0919. Min Act: -0.0001

Data Index: 335089 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0883. Min Act: -0.0002

Data Index: 258306 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0903. Min Act: -0.0001

Data Index: 571731 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1155102 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1328911 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1452 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0873. Min Act: -0.0002

Data Index: 566461 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1188086 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0903. Min Act: -0.0002

Data Index: 705953 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1242270 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0899. Min Act: -0.0002

Data Index: 461745 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1037622 (C4 (Web Text))

Max Activating Token Index: 594