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

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

Neuron 1233 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1645013 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1503855 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1485331 (Python Code)

Max Activating Token Index: 981

Text #3

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1391115 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1455575 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1386238 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1579602 (Python Code)

Max Activating Token Index: 65

Text #7

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1655844 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1567002 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1554355 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1555214 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1417961 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1393054 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1360637 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1423156 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1616127 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1596409 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1624747 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1600041 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1634453 (Python Code)

Max Activating Token Index: 338