Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 570 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1480357 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1412897 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1617737 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1654060 (Python Code)

Max Activating Token Index: 100

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0488. Min Act: -0.0003

Data Index: 275744 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0487. Min Act: -0.0003

Data Index: 273508 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1377510 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0489. Min Act: -0.0003

Data Index: 282912 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0485. Min Act: -0.0003

Data Index: 971340 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0472. Min Act: -0.0003

Data Index: 59857 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1644610 (Python Code)

Max Activating Token Index: 716

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1491973 (Python Code)

Max Activating Token Index: 367

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1360763 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0443. Min Act: -0.0003

Data Index: 239236 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0453. Min Act: -0.0003

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1094303 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0461. Min Act: -0.0003

Data Index: 193508 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0456. Min Act: -0.0003

Data Index: 90799 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1431904 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0465. Min Act: -0.0003

Data Index: 633160 (C4 (Web Text))

Max Activating Token Index: 630