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

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

Neuron 392 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1071178 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1430899 (Python Code)

Max Activating Token Index: 559

Text #2

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1345546 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1707. Min Act: -0.0001

Data Index: 259531 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1694. Min Act: -0.0001

Data Index: 98475 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1681. Min Act: -0.0001

Data Index: 544135 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1617. Min Act: -0.0001

Data Index: 73339 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1547. Min Act: -0.0001

Data Index: 295157 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1693. Min Act: -0.0001

Data Index: 63257 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1591. Min Act: -0.0001

Data Index: 419680 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1577. Min Act: -0.0001

Data Index: 978566 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1465. Min Act: -0.0001

Data Index: 194281 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1465. Min Act: -0.0001

Data Index: 98723 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1502. Min Act: -0.0001

Data Index: 258932 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1510. Min Act: -0.0001

Data Index: 92483 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1346659 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1431. Min Act: -0.0001

Data Index: 670543 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1488. Min Act: -0.0001

Data Index: 964568 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1477. Min Act: -0.0001

Data Index: 830391 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1524. Min Act: -0.0001

Data Index: 16681 (C4 (Web Text))

Max Activating Token Index: 222