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

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

Neuron 20 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: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0006

Data Index: 834123 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0139. Min Act: -0.0006

Data Index: 902046 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0139. Min Act: -0.0006

Data Index: 20580 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0139. Min Act: -0.0006

Data Index: 521965 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0138. Min Act: -0.0006

Data Index: 609566 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1146182 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1241360 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0135. Min Act: -0.0006

Data Index: 929033 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0006

Data Index: 385229 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0006

Data Index: 92151 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1252056 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0126. Min Act: -0.0006

Data Index: 415694 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0006

Data Index: 145636 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0006

Data Index: 505228 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0006

Data Index: 932055 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0128. Min Act: -0.0006

Data Index: 81916 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0128. Min Act: -0.0006

Data Index: 733433 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 681582 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1175354 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1054576 (C4 (Web Text))

Max Activating Token Index: 1000