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

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

Neuron 2584 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7840. Min Range: -2.7840

Max Act: 2.7840. Min Act: -0.0000

Data Index: 179647 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 2.7840. Min Range: -2.7840

Max Act: 2.0732. Min Act: -0.0000

Data Index: 1511620 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 2.7840. Min Range: -2.7840

Max Act: 2.0774. Min Act: -0.0000

Data Index: 187047 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.8968. Min Act: -0.0000

Data Index: 1153733 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.9140. Min Act: -0.0000

Data Index: 896667 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7651. Min Act: -0.0000

Data Index: 3640 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.8640. Min Act: -0.0000

Data Index: 386336 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.9550. Min Act: -0.0000

Data Index: 104632 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1329593 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1488930 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1325480 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.9208. Min Act: -0.0000

Data Index: 944832 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.8004. Min Act: -0.0000

Data Index: 200802 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7806. Min Act: -0.0000

Data Index: 887203 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7658. Min Act: -0.0000

Data Index: 471337 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.6667. Min Act: -0.0000

Data Index: 729687 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.6528. Min Act: -0.0000

Data Index: 789925 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7440. Min Act: -0.0000

Data Index: 544154 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7181. Min Act: -0.0000

Data Index: 365286 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 2.7840. Min Range: -2.7840

Max Act: 1.7216. Min Act: -0.0000

Data Index: 124513 (C4 (Web Text))

Max Activating Token Index: 785