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

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

Neuron 2638 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.5671. Min Act: -0.0000

Data Index: 586015 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1128631 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.2793. Min Act: -0.0000

Data Index: 763622 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.2390. Min Act: -0.0000

Data Index: 411602 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1058749 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1199938 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.0760. Min Act: -0.0000

Data Index: 474429 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1073143 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.0816. Min Act: -0.0000

Data Index: 6755 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.0665. Min Act: -0.0000

Data Index: 671381 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.1153. Min Act: -0.0000

Data Index: 804525 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.1153. Min Act: -0.0000

Data Index: 966603 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.0674. Min Act: -0.0000

Data Index: 812172 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.9876. Min Act: -0.0000

Data Index: 509751 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1073613 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1160627 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.9627. Min Act: -0.0000

Data Index: 831256 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.9916. Min Act: -0.0000

Data Index: 865818 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.9629. Min Act: -0.0000

Data Index: 455350 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.9910. Min Act: -0.0000

Data Index: 991267 (C4 (Web Text))

Max Activating Token Index: 600