Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 768 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0004

Data Index: 1547040 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0161. Min Act: -0.0004

Data Index: 1458094 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0146. Min Act: -0.0004

Data Index: 1532073 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1596213 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0144. Min Act: -0.0004

Data Index: 1431918 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0141. Min Act: -0.0004

Data Index: 1588036 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1425837 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0134. Min Act: -0.0004

Data Index: 1587259 (Python Code)

Max Activating Token Index: 229

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0137. Min Act: -0.0004

Data Index: 1502381 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0134. Min Act: -0.0004

Data Index: 1542834 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0133. Min Act: -0.0004

Data Index: 1562335 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1588266 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1434590 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1634611 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1582117 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1447161 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1458035 (Python Code)

Max Activating Token Index: 261

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1537744 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0127. Min Act: -0.0004

Data Index: 1534804 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1462413 (Python Code)

Max Activating Token Index: 316