Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4008 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.6148. Min Act: -0.0000

Data Index: 562135 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.6598. Min Act: -0.0000

Data Index: 1742304 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.1542. Min Act: -0.0000

Data Index: 1384278 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.5988. Min Act: -0.0000

Data Index: 1547039 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.4020. Min Act: -0.0000

Data Index: 1555014 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.8345. Min Act: -0.0000

Data Index: 1845125 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.1467. Min Act: -0.0000

Data Index: 1341633 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.9720. Min Act: -0.0000

Data Index: 1244307 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.4477. Min Act: -0.0000

Data Index: 1116482 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.1412. Min Act: -0.0000

Data Index: 1573469 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.9874. Min Act: -0.0000

Data Index: 1882461 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.2598. Min Act: -0.0000

Data Index: 986598 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.9422. Min Act: -0.0000

Data Index: 1209333 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.7304. Min Act: -0.0000

Data Index: 1236265 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.6814. Min Act: -0.0000

Data Index: 949963 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.7445. Min Act: -0.0000

Data Index: 1505344 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 3.6598. Min Range: -3.6598

Max Act: 3.0880. Min Act: -0.0000

Data Index: 1557511 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.9104. Min Act: -0.0000

Data Index: 1331525 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.8392. Min Act: -0.0000

Data Index: 1770154 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 3.6598. Min Range: -3.6598

Max Act: 2.5499. Min Act: -0.0000

Data Index: 957862 (The Pile)

Max Activating Token Index: 674