Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3010 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6645. Min Act: -0.0001

Data Index: 537093 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6555. Min Act: -0.0001

Data Index: 450439 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6828. Min Act: -0.0001

Data Index: 295897 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6940. Min Act: -0.0001

Data Index: 228785 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6650. Min Act: -0.0001

Data Index: 978740 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6406. Min Act: -0.0001

Data Index: 1026536 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6400. Min Act: -0.0001

Data Index: 447241 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6620. Min Act: -0.0002

Data Index: 304202 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6234. Min Act: -0.0001

Data Index: 829785 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6607. Min Act: -0.0001

Data Index: 1042405 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6535. Min Act: -0.0001

Data Index: 435204 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5807. Min Act: -0.0001

Data Index: 1126993 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6299. Min Act: -0.0001

Data Index: 221929 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6440. Min Act: -0.0001

Data Index: 1202941 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1152890 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6091. Min Act: -0.0001

Data Index: 1042445 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5644. Min Act: -0.0001

Data Index: 1007909 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5948. Min Act: -0.0001

Data Index: 1207749 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5920. Min Act: -0.0001

Data Index: 230142 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6076. Min Act: -0.0001

Data Index: 744441 (C4 (Web Text))

Max Activating Token Index: 105