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

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

Neuron 1507 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.9798. Min Act: -0.0000

Data Index: 1068758 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.7022. Min Act: -0.0000

Data Index: 1114493 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.4236. Min Act: -0.0000

Data Index: 1120647 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.7197. Min Act: -0.0000

Data Index: 525549 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.3908. Min Act: -0.0000

Data Index: 669317 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.6138. Min Act: -0.0001

Data Index: 1088020 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.5516. Min Act: -0.0000

Data Index: 559716 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.0852. Min Act: -0.0000

Data Index: 595800 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.4543. Min Act: -0.0000

Data Index: 581356 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.3960. Min Act: -0.0000

Data Index: 127908 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.1492. Min Act: -0.0000

Data Index: 822360 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 2.9798. Min Range: -2.9798

Max Act: 1.9923. Min Act: -0.0000

Data Index: 1128863 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.2891. Min Act: -0.0000

Data Index: 1219232 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1181176 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.0541. Min Act: -0.0000

Data Index: 817682 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 2.9798. Min Range: -2.9798

Max Act: 1.9949. Min Act: -0.0000

Data Index: 443911 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.3706. Min Act: -0.0000

Data Index: 541851 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.2437. Min Act: -0.0001

Data Index: 164033 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.1059. Min Act: -0.0000

Data Index: 816737 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.1287. Min Act: -0.0000

Data Index: 438273 (C4 (Web Text))

Max Activating Token Index: 661