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

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

Neuron 3648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3659. Min Range: -3.3659

Max Act: 3.3659. Min Act: -0.0000

Data Index: 142256 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.3766. Min Act: -0.0000

Data Index: 664185 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.4522. Min Act: -0.0000

Data Index: 666463 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.4571. Min Act: -0.0000

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.3622. Min Act: -0.0000

Data Index: 501852 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.3722. Min Act: -0.0000

Data Index: 1118292 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.2969. Min Act: -0.0000

Data Index: 95492 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.1922. Min Act: -0.0000

Data Index: 1308668 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.1723. Min Act: -0.0000

Data Index: 1128369 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.2047. Min Act: -0.0000

Data Index: 631171 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.1457. Min Act: -0.0000

Data Index: 252726 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.3659. Min Range: -3.3659

Max Act: 2.1084. Min Act: -0.0000

Data Index: 846963 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.9547. Min Act: -0.0000

Data Index: 1161998 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.9764. Min Act: -0.0000

Data Index: 290736 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.8072. Min Act: -0.0000

Data Index: 916754 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.7971. Min Act: -0.0000

Data Index: 878321 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.7561. Min Act: -0.0000

Data Index: 519857 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.7782. Min Act: -0.0000

Data Index: 1172990 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.6892. Min Act: -0.0000

Data Index: 921222 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 3.3659. Min Range: -3.3659

Max Act: 1.7755. Min Act: -0.0000

Data Index: 86139 (C4 (Web Text))

Max Activating Token Index: 95