Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8995. Min Act: -0.0001

Data Index: 476878 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8442. Min Act: -0.0001

Data Index: 898142 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7965. Min Act: -0.0001

Data Index: 681992 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8184. Min Act: -0.0001

Data Index: 663118 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7717. Min Act: -0.0001

Data Index: 1078567 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1211708 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7152. Min Act: -0.0001

Data Index: 304240 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7284. Min Act: -0.0001

Data Index: 1000924 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7201. Min Act: -0.0001

Data Index: 1256149 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7157. Min Act: -0.0001

Data Index: 866917 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6911. Min Act: -0.0000

Data Index: 522282 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7324. Min Act: -0.0001

Data Index: 639346 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7098. Min Act: -0.0001

Data Index: 665507 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1215591 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7288. Min Act: -0.0001

Data Index: 285436 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6802. Min Act: -0.0001

Data Index: 910804 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6889. Min Act: -0.0001

Data Index: 328523 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7355. Min Act: -0.0001

Data Index: 511342 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6842. Min Act: -0.0000

Data Index: 760697 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6414. Min Act: -0.0001

Data Index: 557831 (C4 (Web Text))

Max Activating Token Index: 770