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

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

Neuron 3889 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.3568. Min Act: -0.0002

Data Index: 589167 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.3792. Min Act: -0.0002

Data Index: 179155 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.2944. Min Act: -0.0002

Data Index: 264763 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.2544. Min Act: -0.0002

Data Index: 104785 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.1292. Min Act: -0.0002

Data Index: 1216050 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.1230. Min Act: -0.0002

Data Index: 1197904 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.1449. Min Act: -0.0002

Data Index: 825591 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0817. Min Act: -0.0002

Data Index: 717008 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0981. Min Act: -0.0002

Data Index: 503904 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0981. Min Act: -0.0002

Data Index: 1195456 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0981. Min Act: -0.0002

Data Index: 744898 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0981. Min Act: -0.0002

Data Index: 453915 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0981. Min Act: -0.0002

Data Index: 699642 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0981. Min Act: -0.0002

Data Index: 8047 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.1320. Min Act: -0.0002

Data Index: 457790 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.1098. Min Act: -0.0002

Data Index: 1290350 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0552. Min Act: -0.0002

Data Index: 771101 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0835. Min Act: -0.0002

Data Index: 308612 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.1131. Min Act: -0.0002

Data Index: 706005 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 2.3792. Min Range: -2.3792

Max Act: 2.0919. Min Act: -0.0002

Data Index: 531146 (C4 (Web Text))

Max Activating Token Index: 437