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

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

Neuron 14 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: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0006

Data Index: 490338 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0131. Min Act: -0.0006

Data Index: 762432 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0126. Min Act: -0.0006

Data Index: 721293 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0125. Min Act: -0.0006

Data Index: 79355 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0122. Min Act: -0.0006

Data Index: 940068 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0120. Min Act: -0.0006

Data Index: 767226 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0122. Min Act: -0.0006

Data Index: 894920 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0118. Min Act: -0.0006

Data Index: 39045 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0115. Min Act: -0.0006

Data Index: 375147 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0112. Min Act: -0.0006

Data Index: 573728 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0114. Min Act: -0.0006

Data Index: 11863 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0111. Min Act: -0.0006

Data Index: 887417 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0111. Min Act: -0.0006

Data Index: 398410 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0113. Min Act: -0.0006

Data Index: 184029 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0110. Min Act: -0.0006

Data Index: 543969 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0115. Min Act: -0.0006

Data Index: 555454 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1016391 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1142517 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0110. Min Act: -0.0005

Data Index: 1315502 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0109. Min Act: -0.0006

Data Index: 480717 (C4 (Web Text))

Max Activating Token Index: 54