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

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

Neuron 935 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0112. Min Act: -0.0003

Data Index: 358546 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0107. Min Act: -0.0003

Data Index: 233850 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1282582 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0111. Min Act: -0.0003

Data Index: 304373 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0110. Min Act: -0.0003

Data Index: 308721 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0107. Min Act: -0.0003

Data Index: 686887 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0107. Min Act: -0.0003

Data Index: 879183 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1508329 (Python Code)

Max Activating Token Index: 658

Text #8

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0096. Min Act: -0.0003

Data Index: 441328 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0107. Min Act: -0.0003

Data Index: 270685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1107550 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1072636 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0102. Min Act: -0.0003

Data Index: 96887 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1585285 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1364808 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1524414 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1457484 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1065182 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1171222 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0096. Min Act: -0.0003

Data Index: 169877 (C4 (Web Text))

Max Activating Token Index: 1023