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

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

Neuron 5442 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2495. Min Range: -2.2495

Max Act: 2.2495. Min Act: -0.0000

Data Index: 1604514 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 2.2495. Min Range: -2.2495

Max Act: 2.0459. Min Act: -0.0000

Data Index: 1380654 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.9824. Min Act: -0.0000

Data Index: 1480757 (Python Code)

Max Activating Token Index: 773

Text #3

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.9625. Min Act: -0.0000

Data Index: 1389054 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.7418. Min Act: -0.0000

Data Index: 1504152 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.9100. Min Act: -0.0000

Data Index: 1608619 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1491300 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.7151. Min Act: -0.0000

Data Index: 1617040 (Python Code)

Max Activating Token Index: 626

Text #8

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1548457 (Python Code)

Max Activating Token Index: 571

Text #9

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.5113. Min Act: -0.0000

Data Index: 1575649 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.6462. Min Act: -0.0000

Data Index: 1625808 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.4517. Min Act: -0.0000

Data Index: 761283 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1600562 (Python Code)

Max Activating Token Index: 808

Text #13

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.4887. Min Act: -0.0000

Data Index: 791344 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.4501. Min Act: -0.0000

Data Index: 509819 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.4415. Min Act: -0.0000

Data Index: 1139327 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1572262 (Python Code)

Max Activating Token Index: 906

Text #17

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.3769. Min Act: -0.0000

Data Index: 1636577 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.3138. Min Act: -0.0000

Data Index: 1638471 (Python Code)

Max Activating Token Index: 352

Text #19

Max Range: 2.2495. Min Range: -2.2495

Max Act: 1.3112. Min Act: -0.0000

Data Index: 245284 (C4 (Web Text))

Max Activating Token Index: 58