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

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

Neuron 4 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0006

Data Index: 717298 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0006

Data Index: 662578 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0151. Min Act: -0.0006

Data Index: 977770 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0143. Min Act: -0.0006

Data Index: 881555 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0154. Min Act: -0.0006

Data Index: 724630 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1078017 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0149. Min Act: -0.0006

Data Index: 170056 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0153. Min Act: -0.0006

Data Index: 869973 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0133. Min Act: -0.0006

Data Index: 68240 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0146. Min Act: -0.0006

Data Index: 42282 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0135. Min Act: -0.0006

Data Index: 289714 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0138. Min Act: -0.0006

Data Index: 492446 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0134. Min Act: -0.0006

Data Index: 598471 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0131. Min Act: -0.0006

Data Index: 666937 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0144. Min Act: -0.0006

Data Index: 859314 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1159400 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0126. Min Act: -0.0006

Data Index: 555746 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0129. Min Act: -0.0006

Data Index: 187898 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0126. Min Act: -0.0006

Data Index: 446951 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0132. Min Act: -0.0006

Data Index: 111061 (C4 (Web Text))

Max Activating Token Index: 353