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

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

Neuron 1873 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0003

Data Index: 685208 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1190429 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1349855 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0155. Min Act: -0.0003

Data Index: 577096 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0155. Min Act: -0.0003

Data Index: 10364 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1617829 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0147. Min Act: -0.0004

Data Index: 216783 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0143. Min Act: -0.0003

Data Index: 775013 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0137. Min Act: -0.0004

Data Index: 304104 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0142. Min Act: -0.0003

Data Index: 168506 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0139. Min Act: -0.0003

Data Index: 704958 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0135. Min Act: -0.0004

Data Index: 596396 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0129. Min Act: -0.0003

Data Index: 795634 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1464245 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0131. Min Act: -0.0003

Data Index: 33919 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0133. Min Act: -0.0004

Data Index: 824502 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1259411 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0131. Min Act: -0.0003

Data Index: 386509 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1580574 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1158943 (C4 (Web Text))

Max Activating Token Index: 123