Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4372 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0002

Data Index: 467777 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0140. Min Act: -0.0002

Data Index: 656824 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1129780 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0134. Min Act: -0.0002

Data Index: 261333 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0134. Min Act: -0.0002

Data Index: 349383 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0134. Min Act: -0.0002

Data Index: 978738 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0002

Data Index: 146810 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0133. Min Act: -0.0002

Data Index: 21115 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0135. Min Act: -0.0002

Data Index: 690699 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1190037 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0002

Data Index: 376193 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0002

Data Index: 644822 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1103081 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0129. Min Act: -0.0002

Data Index: 700200 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0129. Min Act: -0.0002

Data Index: 80260 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1254768 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0127. Min Act: -0.0002

Data Index: 932461 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0125. Min Act: -0.0002

Data Index: 729935 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1314861 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0127. Min Act: -0.0002

Data Index: 302383 (C4 (Web Text))

Max Activating Token Index: 561