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

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

Neuron 1597 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1162856 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.1015. Min Act: -0.0000

Data Index: 21479 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.0896. Min Act: -0.0000

Data Index: 396024 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.1468. Min Act: -0.0000

Data Index: 673189 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.0239. Min Act: -0.0000

Data Index: 882104 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1649104 (Python Code)

Max Activating Token Index: 536

Text #6

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9569. Min Act: -0.0000

Data Index: 766141 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1426224 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.0493. Min Act: -0.0000

Data Index: 459339 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1548678 (Python Code)

Max Activating Token Index: 478

Text #10

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1395941 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9353. Min Act: -0.0000

Data Index: 819411 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8762. Min Act: -0.0000

Data Index: 101058 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9101. Min Act: -0.0000

Data Index: 313301 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9102. Min Act: -0.0000

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1469435 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8308. Min Act: -0.0000

Data Index: 439672 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1587690 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9400. Min Act: -0.0000

Data Index: 986592 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8362. Min Act: 0.0000

Data Index: 1462163 (Python Code)

Max Activating Token Index: 739