Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1622 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9432. Min Act: -0.0001

Data Index: 1502356 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8192. Min Act: -0.0001

Data Index: 1574071 (Python Code)

Max Activating Token Index: 730

Text #2

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7360. Min Act: -0.0001

Data Index: 1384492 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6927. Min Act: -0.0001

Data Index: 1397801 (Python Code)

Max Activating Token Index: 665

Text #4

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1455396 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7126. Min Act: -0.0001

Data Index: 1527706 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6667. Min Act: -0.0001

Data Index: 1610734 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1377333 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6621. Min Act: -0.0001

Data Index: 1392721 (Python Code)

Max Activating Token Index: 411

Text #9

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1545839 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6393. Min Act: -0.0001

Data Index: 1541392 (Python Code)

Max Activating Token Index: 755

Text #11

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.5949. Min Act: -0.0001

Data Index: 1466058 (Python Code)

Max Activating Token Index: 460

Text #12

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.5789. Min Act: -0.0001

Data Index: 1457251 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.5762. Min Act: -0.0001

Data Index: 1378022 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6070. Min Act: -0.0001

Data Index: 1549456 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6147. Min Act: -0.0001

Data Index: 1404247 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6593. Min Act: -0.0001

Data Index: 775472 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.5812. Min Act: -0.0001

Data Index: 1452184 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1456351 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6014. Min Act: -0.0001

Data Index: 1366688 (Python Code)

Max Activating Token Index: 92