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

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

Neuron 1503 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: 0.0167. Min Range: -0.0167

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1344139 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1345810 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1591075 (Python Code)

Max Activating Token Index: 838

Text #3

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1655212 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0151. Min Act: -0.0006

Data Index: 74374 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1090579 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1118283 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1617290 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1399252 (Python Code)

Max Activating Token Index: 913

Text #9

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1426646 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1495970 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0140. Min Act: -0.0006

Data Index: 458273 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0139. Min Act: -0.0006

Data Index: 913019 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1483706 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1641973 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1481723 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1366424 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1472616 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1449279 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1515586 (Python Code)

Max Activating Token Index: 654