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

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

Neuron 1781 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4930. Min Act: -0.0001

Data Index: 471464 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3915. Min Act: -0.0001

Data Index: 1022611 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4344. Min Act: -0.0001

Data Index: 150468 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4109. Min Act: -0.0001

Data Index: 179070 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1048934 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3912. Min Act: -0.0001

Data Index: 575966 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4144. Min Act: -0.0001

Data Index: 1350198 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4304. Min Act: -0.0001

Data Index: 418487 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4413. Min Act: -0.0001

Data Index: 748682 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4143. Min Act: -0.0001

Data Index: 727372 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4158. Min Act: -0.0001

Data Index: 77794 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4120. Min Act: -0.0001

Data Index: 3720 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4101. Min Act: -0.0001

Data Index: 240962 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1162735 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3903. Min Act: -0.0001

Data Index: 123403 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3493. Min Act: -0.0001

Data Index: 269511 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3979. Min Act: -0.0001

Data Index: 688004 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3967. Min Act: -0.0001

Data Index: 497070 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3972. Min Act: -0.0001

Data Index: 1165620 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3495. Min Act: -0.0001

Data Index: 54946 (C4 (Web Text))

Max Activating Token Index: 636