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

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

Neuron 4683 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1573303 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1465480 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0544. Min Act: -0.0001

Data Index: 322135 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1608913 (Python Code)

Max Activating Token Index: 159

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1575400 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1279081 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1646500 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0477. Min Act: -0.0000

Data Index: 991332 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0522. Min Act: -0.0001

Data Index: 255079 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1352385 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1532100 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1089329 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0485. Min Act: -0.0000

Data Index: 339620 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1224654 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1511055 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1524797 (Python Code)

Max Activating Token Index: 252

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0516. Min Act: -0.0000

Data Index: 580295 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0455. Min Act: -0.0001

Data Index: 145994 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1653380 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1238694 (C4 (Web Text))

Max Activating Token Index: 26