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

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

Neuron 773 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3853. Min Act: -0.0001

Data Index: 712327 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.4006. Min Act: -0.0001

Data Index: 331146 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.4360. Min Act: -0.0001

Data Index: 449532 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3166. Min Act: -0.0001

Data Index: 73985 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3655. Min Act: -0.0001

Data Index: 122780 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.4106. Min Act: -0.0001

Data Index: 892530 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3914. Min Act: -0.0001

Data Index: 658394 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3846. Min Act: -0.0001

Data Index: 537669 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3983. Min Act: -0.0001

Data Index: 1087688 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3947. Min Act: -0.0001

Data Index: 1339039 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3659. Min Act: -0.0001

Data Index: 855553 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3661. Min Act: -0.0001

Data Index: 1133594 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3651. Min Act: -0.0001

Data Index: 1143911 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3630. Min Act: -0.0001

Data Index: 890375 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3759. Min Act: -0.0001

Data Index: 154098 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1108049 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3590. Min Act: -0.0001

Data Index: 67404 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3730. Min Act: -0.0001

Data Index: 1124194 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3872. Min Act: -0.0001

Data Index: 155189 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3351. Min Act: -0.0001

Data Index: 31993 (C4 (Web Text))

Max Activating Token Index: 619