Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1112 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0006

Data Index: 153207 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0509. Min Act: -0.0006

Data Index: 796173 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0515. Min Act: -0.0006

Data Index: 108123 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0499. Min Act: -0.0006

Data Index: 753215 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0482. Min Act: -0.0006

Data Index: 726775 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0490. Min Act: -0.0006

Data Index: 304576 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0476. Min Act: -0.0006

Data Index: 5573 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0497. Min Act: -0.0006

Data Index: 19048 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0463. Min Act: -0.0006

Data Index: 1243958 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1065922 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0451. Min Act: -0.0006

Data Index: 970433 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0470. Min Act: -0.0006

Data Index: 490797 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0445. Min Act: -0.0006

Data Index: 283199 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0467. Min Act: -0.0006

Data Index: 1018577 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0467. Min Act: -0.0006

Data Index: 216214 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0474. Min Act: -0.0006

Data Index: 904086 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0451. Min Act: -0.0006

Data Index: 1192271 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0490. Min Act: -0.0006

Data Index: 893092 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0469. Min Act: -0.0006

Data Index: 1185622 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0462. Min Act: -0.0006

Data Index: 432026 (C4 (Web Text))

Max Activating Token Index: 614