Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3069 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0099. Min Act: -0.0002

Data Index: 501570 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0090. Min Act: -0.0002

Data Index: 548886 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0090. Min Act: -0.0002

Data Index: 217238 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1012990 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0002

Data Index: 830857 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0002

Data Index: 619091 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0002

Data Index: 139468 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0002

Data Index: 527881 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1065452 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0002

Data Index: 513400 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0002

Data Index: 315823 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1072439 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0002

Data Index: 944040 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0002

Data Index: 741238 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0002

Data Index: 568086 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1348139 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1166293 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0083. Min Act: -0.0002

Data Index: 281646 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0083. Min Act: -0.0002

Data Index: 473643 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0002

Data Index: 322265 (C4 (Web Text))

Max Activating Token Index: 370