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

Dataset: The Pile

Neuron 1256 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3442. Min Act: -0.0001

Data Index: 1277183 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3038. Min Act: -0.0001

Data Index: 316904 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1150533 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1482167 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1626198 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2458. Min Act: -0.0001

Data Index: 916686 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2799. Min Act: -0.0001

Data Index: 480794 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1737728 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1286107 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1402081 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1177514 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2668. Min Act: -0.0001

Data Index: 1648306 (The Pile)

Max Activating Token Index: 557

Text #12

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1815608 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2575. Min Act: -0.0001

Data Index: 841239 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2463. Min Act: -0.0001

Data Index: 15762 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2522. Min Act: -0.0001

Data Index: 905232 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2457. Min Act: -0.0001

Data Index: 710324 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1493342 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2493. Min Act: -0.0001

Data Index: 1739676 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2359. Min Act: -0.0001

Data Index: 718540 (The Pile)

Max Activating Token Index: 498