Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 653 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0005

Data Index: 1424582 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0107. Min Act: -0.0006

Data Index: 942852 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1418228 (Python Code)

Max Activating Token Index: 536

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0106. Min Act: -0.0006

Data Index: 875745 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1608561 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1538403 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0006

Data Index: 674456 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1201915 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0101. Min Act: -0.0006

Data Index: 322584 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1330272 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0102. Min Act: -0.0006

Data Index: 343824 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0097. Min Act: -0.0006

Data Index: 766249 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1075986 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0097. Min Act: -0.0006

Data Index: 502708 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0097. Min Act: -0.0006

Data Index: 921515 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0095. Min Act: -0.0006

Data Index: 901479 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1630190 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0094. Min Act: -0.0006

Data Index: 17327 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1324697 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0095. Min Act: -0.0006

Data Index: 221807 (C4 (Web Text))

Max Activating Token Index: 447