Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3577 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2681. Min Act: -0.0001

Data Index: 510968 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1685. Min Act: -0.0001

Data Index: 937727 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1735. Min Act: -0.0001

Data Index: 263033 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1572. Min Act: -0.0001

Data Index: 863985 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1600. Min Act: -0.0001

Data Index: 519883 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1687. Min Act: -0.0001

Data Index: 945042 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1321265 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1610. Min Act: -0.0001

Data Index: 715887 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1592. Min Act: -0.0001

Data Index: 610300 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1517. Min Act: -0.0001

Data Index: 745045 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1604. Min Act: -0.0001

Data Index: 621561 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1339. Min Act: -0.0001

Data Index: 962091 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1367. Min Act: -0.0001

Data Index: 914818 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1295517 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1341. Min Act: -0.0001

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1357. Min Act: -0.0001

Data Index: 725055 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1266. Min Act: -0.0001

Data Index: 969113 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1303. Min Act: -0.0001

Data Index: 734735 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1515. Min Act: -0.0001

Data Index: 11172 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.1347. Min Act: -0.0001

Data Index: 572154 (C4 (Web Text))

Max Activating Token Index: 427