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

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

Neuron 3682 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.8493. Min Act: -0.0001

Data Index: 726151 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.7750. Min Act: -0.0001

Data Index: 1608927 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5302. Min Act: -0.0001

Data Index: 1514282 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.5456. Min Act: -0.0001

Data Index: 1500825 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.3408. Min Act: -0.0001

Data Index: 1451739 (Python Code)

Max Activating Token Index: 793

Text #5

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.2875. Min Act: -0.0001

Data Index: 1622915 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.2915. Min Act: -0.0001

Data Index: 1406957 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.2284. Min Act: -0.0001

Data Index: 1562887 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.2820. Min Act: -0.0001

Data Index: 1559744 (Python Code)

Max Activating Token Index: 259

Text #9

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.1727. Min Act: -0.0001

Data Index: 1153637 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.1702. Min Act: -0.0001

Data Index: 1367640 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.1824. Min Act: -0.0001

Data Index: 1032628 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.1044. Min Act: -0.0001

Data Index: 1110829 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.1404. Min Act: -0.0001

Data Index: 1635025 (Python Code)

Max Activating Token Index: 630

Text #14

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.1782. Min Act: -0.0001

Data Index: 1420157 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.2218. Min Act: -0.0001

Data Index: 1515926 (Python Code)

Max Activating Token Index: 271

Text #16

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.0874. Min Act: -0.0001

Data Index: 1366965 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.1989. Min Act: -0.0001

Data Index: 1630042 (Python Code)

Max Activating Token Index: 686

Text #18

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.0250. Min Act: -0.0001

Data Index: 1413971 (Python Code)

Max Activating Token Index: 503

Text #19

Max Range: 1.8493. Min Range: -1.8493

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1181073 (C4 (Web Text))

Max Activating Token Index: 497