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

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

Neuron 2660 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: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0003

Data Index: 325698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1118135 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0003

Data Index: 518629 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0003

Data Index: 739261 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0105. Min Act: -0.0003

Data Index: 237337 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0123. Min Act: -0.0003

Data Index: 954813 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0004

Data Index: 1611910 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1428231 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0103. Min Act: -0.0003

Data Index: 161642 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0003

Data Index: 122245 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0003

Data Index: 78831 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0003

Data Index: 172225 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1369534 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1043644 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0115. Min Act: -0.0003

Data Index: 35353 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0087. Min Act: -0.0003

Data Index: 267050 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0103. Min Act: -0.0003

Data Index: 436114 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0106. Min Act: -0.0004

Data Index: 35686 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0104. Min Act: -0.0003

Data Index: 300082 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0098. Min Act: -0.0003

Data Index: 249811 (C4 (Web Text))

Max Activating Token Index: 858