Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1487 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0146. Min Act: -0.0003

Data Index: 861667 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0152. Min Act: -0.0003

Data Index: 97496 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0147. Min Act: -0.0003

Data Index: 482657 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0141. Min Act: -0.0003

Data Index: 9424 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1154948 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0140. Min Act: -0.0003

Data Index: 742467 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1448072 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0150. Min Act: -0.0003

Data Index: 181789 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0136. Min Act: -0.0003

Data Index: 775306 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1010496 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0130. Min Act: -0.0003

Data Index: 436855 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0130. Min Act: -0.0003

Data Index: 347538 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0121. Min Act: -0.0003

Data Index: 63978 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0127. Min Act: -0.0003

Data Index: 765095 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0136. Min Act: -0.0003

Data Index: 274580 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1067270 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0132. Min Act: -0.0003

Data Index: 901369 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0129. Min Act: -0.0003

Data Index: 448088 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0125. Min Act: -0.0003

Data Index: 108926 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1156722 (C4 (Web Text))

Max Activating Token Index: 437