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

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

Neuron 2492 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1148369 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6416. Min Act: -0.0001

Data Index: 1211159 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1028084 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6532. Min Act: -0.0001

Data Index: 95945 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6148. Min Act: -0.0001

Data Index: 1057253 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6228. Min Act: -0.0001

Data Index: 1029266 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6580. Min Act: -0.0001

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5926. Min Act: -0.0001

Data Index: 450480 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5915. Min Act: -0.0001

Data Index: 1097560 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5901. Min Act: -0.0001

Data Index: 860069 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6316. Min Act: -0.0001

Data Index: 474621 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6046. Min Act: -0.0001

Data Index: 329309 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5990. Min Act: -0.0001

Data Index: 1332133 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5988. Min Act: -0.0001

Data Index: 238345 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5684. Min Act: -0.0001

Data Index: 210085 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5235. Min Act: -0.0001

Data Index: 417493 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5610. Min Act: -0.0001

Data Index: 610993 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5593. Min Act: -0.0001

Data Index: 110471 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5615. Min Act: -0.0001

Data Index: 886720 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5518. Min Act: -0.0001

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 470