Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 672 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0005

Data Index: 624426 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0151. Min Act: -0.0005

Data Index: 817229 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0143. Min Act: -0.0005

Data Index: 39254 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1497363 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0134. Min Act: -0.0005

Data Index: 649215 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0131. Min Act: -0.0005

Data Index: 1616774 (Python Code)

Max Activating Token Index: 962

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1127177 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0132. Min Act: -0.0005

Data Index: 794184 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0128. Min Act: -0.0005

Data Index: 996990 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1480479 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1479043 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0127. Min Act: -0.0005

Data Index: 955173 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1632996 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0126. Min Act: -0.0005

Data Index: 508991 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0128. Min Act: -0.0005

Data Index: 889239 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0126. Min Act: -0.0005

Data Index: 139001 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0124. Min Act: -0.0005

Data Index: 87485 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0126. Min Act: -0.0006

Data Index: 388833 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0125. Min Act: -0.0006

Data Index: 543360 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1638358 (Python Code)

Max Activating Token Index: 1020