Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1902 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4034. Min Act: -0.0001

Data Index: 884040 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1222187 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4169. Min Act: -0.0001

Data Index: 409679 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3874. Min Act: -0.0001

Data Index: 688720 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3860. Min Act: -0.0001

Data Index: 1048226 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3652. Min Act: -0.0001

Data Index: 37840 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3746. Min Act: -0.0001

Data Index: 1137374 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3711. Min Act: -0.0001

Data Index: 483712 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3663. Min Act: -0.0001

Data Index: 907359 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1043219 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3547. Min Act: -0.0001

Data Index: 534565 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3634. Min Act: -0.0001

Data Index: 237194 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3637. Min Act: -0.0001

Data Index: 790313 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3472. Min Act: -0.0001

Data Index: 472292 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3447. Min Act: -0.0001

Data Index: 1358631 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3454. Min Act: -0.0001

Data Index: 172967 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3438. Min Act: -0.0001

Data Index: 812575 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3560. Min Act: -0.0001

Data Index: 892919 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3523. Min Act: -0.0001

Data Index: 193704 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3274. Min Act: -0.0001

Data Index: 1055114 (C4 (Web Text))

Max Activating Token Index: 610