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

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

Neuron 622 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: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0006

Data Index: 394487 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 388051 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 262989 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0006

Data Index: 19790 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0006

Data Index: 436079 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0006

Data Index: 112444 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0006

Data Index: 789111 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0117. Min Act: -0.0006

Data Index: 985636 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1241779 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0006

Data Index: 440592 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1054377 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0112. Min Act: -0.0006

Data Index: 531995 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0006

Data Index: 342061 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0006

Data Index: 194295 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1350339 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1020804 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 254651 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1273839 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 815309 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 80453 (C4 (Web Text))

Max Activating Token Index: 911