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

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

Neuron 3825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.9129. Min Act: -0.0000

Data Index: 924338 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8402. Min Act: -0.0000

Data Index: 636756 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1043140 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1287185 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1011215 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1098725 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7252. Min Act: -0.0000

Data Index: 546599 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6766. Min Act: -0.0001

Data Index: 962481 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6706. Min Act: -0.0001

Data Index: 569084 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7226. Min Act: -0.0000

Data Index: 409579 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6978. Min Act: -0.0001

Data Index: 523706 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6459. Min Act: -0.0001

Data Index: 687368 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6406. Min Act: -0.0000

Data Index: 674280 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6296. Min Act: -0.0001

Data Index: 851428 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6398. Min Act: -0.0001

Data Index: 695861 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1008306 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1067803 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6608. Min Act: -0.0001

Data Index: 1133578 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6734. Min Act: -0.0001

Data Index: 1291749 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1242235 (C4 (Web Text))

Max Activating Token Index: 665