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

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

Neuron 2956 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: 3.5605. Min Range: -3.5605

Max Act: 3.5605. Min Act: -0.0000

Data Index: 771658 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.8175. Min Act: -0.0000

Data Index: 1381368 (Python Code)

Max Activating Token Index: 682

Text #2

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.5006. Min Act: -0.0000

Data Index: 1238328 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.5378. Min Act: -0.0000

Data Index: 344652 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.1527. Min Act: -0.0000

Data Index: 643350 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.3128. Min Act: -0.0000

Data Index: 1642303 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.4497. Min Act: -0.0000

Data Index: 283088 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.1899. Min Act: -0.0000

Data Index: 297578 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.1641. Min Act: -0.0000

Data Index: 335444 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1115628 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.1452. Min Act: -0.0000

Data Index: 898835 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.1464. Min Act: -0.0000

Data Index: 764017 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.0795. Min Act: -0.0000

Data Index: 154256 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 3.5605. Min Range: -3.5605

Max Act: 2.1591. Min Act: -0.0000

Data Index: 716119 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 3.5605. Min Range: -3.5605

Max Act: 1.9991. Min Act: -0.0000

Data Index: 926487 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 3.5605. Min Range: -3.5605

Max Act: 1.8923. Min Act: -0.0000

Data Index: 613508 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 3.5605. Min Range: -3.5605

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1079071 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 3.5605. Min Range: -3.5605

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1565025 (Python Code)

Max Activating Token Index: 669

Text #18

Max Range: 3.5605. Min Range: -3.5605

Max Act: 1.7149. Min Act: -0.0000

Data Index: 794956 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 3.5605. Min Range: -3.5605

Max Act: 1.8062. Min Act: -0.0000

Data Index: 771050 (C4 (Web Text))

Max Activating Token Index: 321