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

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

Neuron 2855 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: 0.1853. Min Range: -0.1853

Max Act: 0.1853. Min Act: -0.0001

Data Index: 224497 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1713. Min Act: -0.0001

Data Index: 268216 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1647. Min Act: -0.0001

Data Index: 103399 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1109604 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1297975 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1284796 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1598. Min Act: -0.0001

Data Index: 242715 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1780. Min Act: -0.0001

Data Index: 917012 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1519. Min Act: -0.0001

Data Index: 757299 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1608. Min Act: -0.0001

Data Index: 575068 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1574. Min Act: -0.0001

Data Index: 673861 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1513. Min Act: -0.0001

Data Index: 695379 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1485. Min Act: -0.0001

Data Index: 205732 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1441. Min Act: -0.0001

Data Index: 92011 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1055762 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1382. Min Act: -0.0001

Data Index: 878783 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1525. Min Act: -0.0001

Data Index: 981892 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1459. Min Act: -0.0001

Data Index: 354159 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1508. Min Act: -0.0001

Data Index: 856726 (C4 (Web Text))

Max Activating Token Index: 166